Commit
•
9537a09
1
Parent(s):
dd42d6e
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- added_tokens.json +40 -0
- merges.txt +0 -0
- mlc-chat-config.json +77 -0
- ndarray-cache.json +2717 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
- params_shard_22.bin +3 -0
- params_shard_23.bin +3 -0
- params_shard_24.bin +3 -0
- params_shard_25.bin +3 -0
- params_shard_26.bin +3 -0
- params_shard_27.bin +3 -0
- params_shard_28.bin +3 -0
- params_shard_29.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_30.bin +3 -0
- params_shard_31.bin +3 -0
- params_shard_32.bin +3 -0
- params_shard_33.bin +3 -0
- params_shard_34.bin +3 -0
- params_shard_35.bin +3 -0
- params_shard_36.bin +3 -0
- params_shard_37.bin +3 -0
- params_shard_38.bin +3 -0
- params_shard_39.bin +3 -0
- params_shard_4.bin +3 -0
- params_shard_40.bin +3 -0
- params_shard_41.bin +3 -0
- params_shard_42.bin +3 -0
- params_shard_43.bin +3 -0
- params_shard_44.bin +3 -0
- params_shard_45.bin +3 -0
- params_shard_46.bin +3 -0
- params_shard_47.bin +3 -0
- params_shard_48.bin +3 -0
- params_shard_49.bin +3 -0
- params_shard_5.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mlc-chat-config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "0.1.0",
|
| 3 |
+
"model_type": "phi",
|
| 4 |
+
"quantization": "q0f16",
|
| 5 |
+
"model_config": {
|
| 6 |
+
"vocab_size": 51200,
|
| 7 |
+
"hidden_size": 2560,
|
| 8 |
+
"intermediate_size": 10240,
|
| 9 |
+
"num_hidden_layers": 20,
|
| 10 |
+
"num_attention_heads": 32,
|
| 11 |
+
"layer_norm_eps": 1e-05,
|
| 12 |
+
"position_embedding_base": 10000.0,
|
| 13 |
+
"partial_rotary_factor": 0.4,
|
| 14 |
+
"num_key_value_heads": 32,
|
| 15 |
+
"context_window_size": 2048,
|
| 16 |
+
"prefill_chunk_size": 2048,
|
| 17 |
+
"head_dim": 80,
|
| 18 |
+
"tensor_parallel_shards": 1,
|
| 19 |
+
"max_batch_size": 128
|
| 20 |
+
},
|
| 21 |
+
"vocab_size": 51200,
|
| 22 |
+
"context_window_size": 2048,
|
| 23 |
+
"sliding_window_size": -1,
|
| 24 |
+
"prefill_chunk_size": 2048,
|
| 25 |
+
"attention_sink_size": -1,
|
| 26 |
+
"tensor_parallel_shards": 1,
|
| 27 |
+
"pipeline_parallel_stages": 1,
|
| 28 |
+
"temperature": 1.0,
|
| 29 |
+
"presence_penalty": 0.0,
|
| 30 |
+
"frequency_penalty": 0.0,
|
| 31 |
+
"repetition_penalty": 1.0,
|
| 32 |
+
"top_p": 1.0,
|
| 33 |
+
"tokenizer_files": [
|
| 34 |
+
"tokenizer.json",
|
| 35 |
+
"merges.txt",
|
| 36 |
+
"added_tokens.json",
|
| 37 |
+
"tokenizer_config.json"
|
| 38 |
+
],
|
| 39 |
+
"tokenizer_info": {
|
| 40 |
+
"token_postproc_method": "byte_level",
|
| 41 |
+
"prepend_space_in_encode": false,
|
| 42 |
+
"strip_space_in_decode": false
|
| 43 |
+
},
|
| 44 |
+
"conv_template": {
|
| 45 |
+
"name": "phi-2",
|
| 46 |
+
"system_template": "{system_message}",
|
| 47 |
+
"system_message": "",
|
| 48 |
+
"system_prefix_token_ids": null,
|
| 49 |
+
"add_role_after_system_message": true,
|
| 50 |
+
"roles": {
|
| 51 |
+
"user": "Instruct",
|
| 52 |
+
"assistant": "Output"
|
| 53 |
+
},
|
| 54 |
+
"role_templates": {
|
| 55 |
+
"user": "{user_message}",
|
| 56 |
+
"assistant": "{assistant_message}",
|
| 57 |
+
"tool": "{tool_message}"
|
| 58 |
+
},
|
| 59 |
+
"messages": [],
|
| 60 |
+
"seps": [
|
| 61 |
+
"\n"
|
| 62 |
+
],
|
| 63 |
+
"role_content_sep": ": ",
|
| 64 |
+
"role_empty_sep": ":",
|
| 65 |
+
"stop_str": [
|
| 66 |
+
"<|endoftext|>"
|
| 67 |
+
],
|
| 68 |
+
"stop_token_ids": [
|
| 69 |
+
50256
|
| 70 |
+
],
|
| 71 |
+
"function_string": "",
|
| 72 |
+
"use_function_calling": false
|
| 73 |
+
},
|
| 74 |
+
"pad_token_id": 0,
|
| 75 |
+
"bos_token_id": 50256,
|
| 76 |
+
"eos_token_id": 50256
|
| 77 |
+
}
|
ndarray-cache.json
ADDED
|
@@ -0,0 +1,2717 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"ParamSize": 205,
|
| 4 |
+
"ParamBytes": 3671255040.0,
|
| 5 |
+
"BitsPerParam": 16.0
|
| 6 |
+
},
|
| 7 |
+
"records": [
|
| 8 |
+
{
|
| 9 |
+
"dataPath": "params_shard_0.bin",
|
| 10 |
+
"format": "raw-shard",
|
| 11 |
+
"nbytes": 262144000,
|
| 12 |
+
"records": [
|
| 13 |
+
{
|
| 14 |
+
"name": "lm_head.linear.weight",
|
| 15 |
+
"shape": [
|
| 16 |
+
51200,
|
| 17 |
+
2560
|
| 18 |
+
],
|
| 19 |
+
"dtype": "float16",
|
| 20 |
+
"format": "f32-to-bf16",
|
| 21 |
+
"nbytes": 262144000,
|
| 22 |
+
"byteOffset": 0
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
+
"md5sum": "f94243661c5a87b38f3bb41b70d6ebf5"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"dataPath": "params_shard_1.bin",
|
| 29 |
+
"format": "raw-shard",
|
| 30 |
+
"nbytes": 52428800,
|
| 31 |
+
"records": [
|
| 32 |
+
{
|
| 33 |
+
"name": "transformer.h.14.mlp.fc1.weight",
|
| 34 |
+
"shape": [
|
| 35 |
+
10240,
|
| 36 |
+
2560
|
| 37 |
+
],
|
| 38 |
+
"dtype": "float16",
|
| 39 |
+
"format": "f32-to-bf16",
|
| 40 |
+
"nbytes": 52428800,
|
| 41 |
+
"byteOffset": 0
|
| 42 |
+
}
|
| 43 |
+
],
|
| 44 |
+
"md5sum": "b13cdf199fa41a6015318c1e9563b5d3"
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"dataPath": "params_shard_2.bin",
|
| 48 |
+
"format": "raw-shard",
|
| 49 |
+
"nbytes": 52428800,
|
| 50 |
+
"records": [
|
| 51 |
+
{
|
| 52 |
+
"name": "transformer.h.14.mlp.fc2.weight",
|
| 53 |
+
"shape": [
|
| 54 |
+
2560,
|
| 55 |
+
10240
|
| 56 |
+
],
|
| 57 |
+
"dtype": "float16",
|
| 58 |
+
"format": "f32-to-bf16",
|
| 59 |
+
"nbytes": 52428800,
|
| 60 |
+
"byteOffset": 0
|
| 61 |
+
}
|
| 62 |
+
],
|
| 63 |
+
"md5sum": "75014792943f75c804cb504bf349ad15"
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"dataPath": "params_shard_3.bin",
|
| 67 |
+
"format": "raw-shard",
|
| 68 |
+
"nbytes": 39321600,
|
| 69 |
+
"records": [
|
| 70 |
+
{
|
| 71 |
+
"name": "transformer.h.14.mixer.Wqkv.weight",
|
| 72 |
+
"shape": [
|
| 73 |
+
7680,
|
| 74 |
+
2560
|
| 75 |
+
],
|
| 76 |
+
"dtype": "float16",
|
| 77 |
+
"format": "f32-to-bf16",
|
| 78 |
+
"nbytes": 39321600,
|
| 79 |
+
"byteOffset": 0
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"md5sum": "d66bbc9ff5c2c4456695dca08d90d680"
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"dataPath": "params_shard_4.bin",
|
| 86 |
+
"format": "raw-shard",
|
| 87 |
+
"nbytes": 52428800,
|
| 88 |
+
"records": [
|
| 89 |
+
{
|
| 90 |
+
"name": "transformer.h.15.mlp.fc1.weight",
|
| 91 |
+
"shape": [
|
| 92 |
+
10240,
|
| 93 |
+
2560
|
| 94 |
+
],
|
| 95 |
+
"dtype": "float16",
|
| 96 |
+
"format": "f32-to-bf16",
|
| 97 |
+
"nbytes": 52428800,
|
| 98 |
+
"byteOffset": 0
|
| 99 |
+
}
|
| 100 |
+
],
|
| 101 |
+
"md5sum": "3ab6bceeac17f3a1ebe76be2153ccc33"
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"dataPath": "params_shard_5.bin",
|
| 105 |
+
"format": "raw-shard",
|
| 106 |
+
"nbytes": 52428800,
|
| 107 |
+
"records": [
|
| 108 |
+
{
|
| 109 |
+
"name": "transformer.h.15.mlp.fc2.weight",
|
| 110 |
+
"shape": [
|
| 111 |
+
2560,
|
| 112 |
+
10240
|
| 113 |
+
],
|
| 114 |
+
"dtype": "float16",
|
| 115 |
+
"format": "f32-to-bf16",
|
| 116 |
+
"nbytes": 52428800,
|
| 117 |
+
"byteOffset": 0
|
| 118 |
+
}
|
| 119 |
+
],
|
| 120 |
+
"md5sum": "cfc960c8f3e40f3f8984b619b578c8f4"
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"dataPath": "params_shard_6.bin",
|
| 124 |
+
"format": "raw-shard",
|
| 125 |
+
"nbytes": 39321600,
|
| 126 |
+
"records": [
|
| 127 |
+
{
|
| 128 |
+
"name": "transformer.h.15.mixer.Wqkv.weight",
|
| 129 |
+
"shape": [
|
| 130 |
+
7680,
|
| 131 |
+
2560
|
| 132 |
+
],
|
| 133 |
+
"dtype": "float16",
|
| 134 |
+
"format": "f32-to-bf16",
|
| 135 |
+
"nbytes": 39321600,
|
| 136 |
+
"byteOffset": 0
|
| 137 |
+
}
|
| 138 |
+
],
|
| 139 |
+
"md5sum": "a1f896b5733dda3e41688a8aa5d48f18"
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"dataPath": "params_shard_7.bin",
|
| 143 |
+
"format": "raw-shard",
|
| 144 |
+
"nbytes": 52428800,
|
| 145 |
+
"records": [
|
| 146 |
+
{
|
| 147 |
+
"name": "transformer.h.16.mlp.fc1.weight",
|
| 148 |
+
"shape": [
|
| 149 |
+
10240,
|
| 150 |
+
2560
|
| 151 |
+
],
|
| 152 |
+
"dtype": "float16",
|
| 153 |
+
"format": "f32-to-bf16",
|
| 154 |
+
"nbytes": 52428800,
|
| 155 |
+
"byteOffset": 0
|
| 156 |
+
}
|
| 157 |
+
],
|
| 158 |
+
"md5sum": "86a3e23a912734667d74787760b4cf14"
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"dataPath": "params_shard_8.bin",
|
| 162 |
+
"format": "raw-shard",
|
| 163 |
+
"nbytes": 52428800,
|
| 164 |
+
"records": [
|
| 165 |
+
{
|
| 166 |
+
"name": "transformer.h.16.mlp.fc2.weight",
|
| 167 |
+
"shape": [
|
| 168 |
+
2560,
|
| 169 |
+
10240
|
| 170 |
+
],
|
| 171 |
+
"dtype": "float16",
|
| 172 |
+
"format": "f32-to-bf16",
|
| 173 |
+
"nbytes": 52428800,
|
| 174 |
+
"byteOffset": 0
|
| 175 |
+
}
|
| 176 |
+
],
|
| 177 |
+
"md5sum": "913b689959d1363a8fb2ca832deb7fb8"
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"dataPath": "params_shard_9.bin",
|
| 181 |
+
"format": "raw-shard",
|
| 182 |
+
"nbytes": 26480640,
|
| 183 |
+
"records": [
|
| 184 |
+
{
|
| 185 |
+
"name": "lm_head.linear.bias",
|
| 186 |
+
"shape": [
|
| 187 |
+
51200
|
| 188 |
+
],
|
| 189 |
+
"dtype": "float16",
|
| 190 |
+
"format": "f32-to-bf16",
|
| 191 |
+
"nbytes": 102400,
|
| 192 |
+
"byteOffset": 0
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"name": "lm_head.ln.bias",
|
| 196 |
+
"shape": [
|
| 197 |
+
2560
|
| 198 |
+
],
|
| 199 |
+
"dtype": "float16",
|
| 200 |
+
"format": "f32-to-bf16",
|
| 201 |
+
"nbytes": 5120,
|
| 202 |
+
"byteOffset": 102400
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"name": "lm_head.ln.weight",
|
| 206 |
+
"shape": [
|
| 207 |
+
2560
|
| 208 |
+
],
|
| 209 |
+
"dtype": "float16",
|
| 210 |
+
"format": "f32-to-bf16",
|
| 211 |
+
"nbytes": 5120,
|
| 212 |
+
"byteOffset": 107520
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"name": "transformer.h.14.ln.bias",
|
| 216 |
+
"shape": [
|
| 217 |
+
2560
|
| 218 |
+
],
|
| 219 |
+
"dtype": "float16",
|
| 220 |
+
"format": "f32-to-bf16",
|
| 221 |
+
"nbytes": 5120,
|
| 222 |
+
"byteOffset": 112640
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"name": "transformer.h.14.ln.weight",
|
| 226 |
+
"shape": [
|
| 227 |
+
2560
|
| 228 |
+
],
|
| 229 |
+
"dtype": "float16",
|
| 230 |
+
"format": "f32-to-bf16",
|
| 231 |
+
"nbytes": 5120,
|
| 232 |
+
"byteOffset": 117760
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"name": "transformer.h.14.mlp.fc1.bias",
|
| 236 |
+
"shape": [
|
| 237 |
+
10240
|
| 238 |
+
],
|
| 239 |
+
"dtype": "float16",
|
| 240 |
+
"format": "f32-to-bf16",
|
| 241 |
+
"nbytes": 20480,
|
| 242 |
+
"byteOffset": 122880
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"name": "transformer.h.14.mlp.fc2.bias",
|
| 246 |
+
"shape": [
|
| 247 |
+
2560
|
| 248 |
+
],
|
| 249 |
+
"dtype": "float16",
|
| 250 |
+
"format": "f32-to-bf16",
|
| 251 |
+
"nbytes": 5120,
|
| 252 |
+
"byteOffset": 143360
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"name": "transformer.h.14.mixer.out_proj.bias",
|
| 256 |
+
"shape": [
|
| 257 |
+
2560
|
| 258 |
+
],
|
| 259 |
+
"dtype": "float16",
|
| 260 |
+
"format": "f32-to-bf16",
|
| 261 |
+
"nbytes": 5120,
|
| 262 |
+
"byteOffset": 148480
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"name": "transformer.h.14.mixer.out_proj.weight",
|
| 266 |
+
"shape": [
|
| 267 |
+
2560,
|
| 268 |
+
2560
|
| 269 |
+
],
|
| 270 |
+
"dtype": "float16",
|
| 271 |
+
"format": "f32-to-bf16",
|
| 272 |
+
"nbytes": 13107200,
|
| 273 |
+
"byteOffset": 153600
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"name": "transformer.h.14.mixer.Wqkv.bias",
|
| 277 |
+
"shape": [
|
| 278 |
+
7680
|
| 279 |
+
],
|
| 280 |
+
"dtype": "float16",
|
| 281 |
+
"format": "f32-to-bf16",
|
| 282 |
+
"nbytes": 15360,
|
| 283 |
+
"byteOffset": 13260800
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"name": "transformer.h.15.ln.bias",
|
| 287 |
+
"shape": [
|
| 288 |
+
2560
|
| 289 |
+
],
|
| 290 |
+
"dtype": "float16",
|
| 291 |
+
"format": "f32-to-bf16",
|
| 292 |
+
"nbytes": 5120,
|
| 293 |
+
"byteOffset": 13276160
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"name": "transformer.h.15.ln.weight",
|
| 297 |
+
"shape": [
|
| 298 |
+
2560
|
| 299 |
+
],
|
| 300 |
+
"dtype": "float16",
|
| 301 |
+
"format": "f32-to-bf16",
|
| 302 |
+
"nbytes": 5120,
|
| 303 |
+
"byteOffset": 13281280
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"name": "transformer.h.15.mlp.fc1.bias",
|
| 307 |
+
"shape": [
|
| 308 |
+
10240
|
| 309 |
+
],
|
| 310 |
+
"dtype": "float16",
|
| 311 |
+
"format": "f32-to-bf16",
|
| 312 |
+
"nbytes": 20480,
|
| 313 |
+
"byteOffset": 13286400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"name": "transformer.h.15.mlp.fc2.bias",
|
| 317 |
+
"shape": [
|
| 318 |
+
2560
|
| 319 |
+
],
|
| 320 |
+
"dtype": "float16",
|
| 321 |
+
"format": "f32-to-bf16",
|
| 322 |
+
"nbytes": 5120,
|
| 323 |
+
"byteOffset": 13306880
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"name": "transformer.h.15.mixer.out_proj.bias",
|
| 327 |
+
"shape": [
|
| 328 |
+
2560
|
| 329 |
+
],
|
| 330 |
+
"dtype": "float16",
|
| 331 |
+
"format": "f32-to-bf16",
|
| 332 |
+
"nbytes": 5120,
|
| 333 |
+
"byteOffset": 13312000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"name": "transformer.h.15.mixer.out_proj.weight",
|
| 337 |
+
"shape": [
|
| 338 |
+
2560,
|
| 339 |
+
2560
|
| 340 |
+
],
|
| 341 |
+
"dtype": "float16",
|
| 342 |
+
"format": "f32-to-bf16",
|
| 343 |
+
"nbytes": 13107200,
|
| 344 |
+
"byteOffset": 13317120
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"name": "transformer.h.15.mixer.Wqkv.bias",
|
| 348 |
+
"shape": [
|
| 349 |
+
7680
|
| 350 |
+
],
|
| 351 |
+
"dtype": "float16",
|
| 352 |
+
"format": "f32-to-bf16",
|
| 353 |
+
"nbytes": 15360,
|
| 354 |
+
"byteOffset": 26424320
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"name": "transformer.h.16.ln.bias",
|
| 358 |
+
"shape": [
|
| 359 |
+
2560
|
| 360 |
+
],
|
| 361 |
+
"dtype": "float16",
|
| 362 |
+
"format": "f32-to-bf16",
|
| 363 |
+
"nbytes": 5120,
|
| 364 |
+
"byteOffset": 26439680
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"name": "transformer.h.16.ln.weight",
|
| 368 |
+
"shape": [
|
| 369 |
+
2560
|
| 370 |
+
],
|
| 371 |
+
"dtype": "float16",
|
| 372 |
+
"format": "f32-to-bf16",
|
| 373 |
+
"nbytes": 5120,
|
| 374 |
+
"byteOffset": 26444800
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"name": "transformer.h.16.mlp.fc1.bias",
|
| 378 |
+
"shape": [
|
| 379 |
+
10240
|
| 380 |
+
],
|
| 381 |
+
"dtype": "float16",
|
| 382 |
+
"format": "f32-to-bf16",
|
| 383 |
+
"nbytes": 20480,
|
| 384 |
+
"byteOffset": 26449920
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"name": "transformer.h.16.mlp.fc2.bias",
|
| 388 |
+
"shape": [
|
| 389 |
+
2560
|
| 390 |
+
],
|
| 391 |
+
"dtype": "float16",
|
| 392 |
+
"format": "f32-to-bf16",
|
| 393 |
+
"nbytes": 5120,
|
| 394 |
+
"byteOffset": 26470400
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"name": "transformer.h.16.mixer.out_proj.bias",
|
| 398 |
+
"shape": [
|
| 399 |
+
2560
|
| 400 |
+
],
|
| 401 |
+
"dtype": "float16",
|
| 402 |
+
"format": "f32-to-bf16",
|
| 403 |
+
"nbytes": 5120,
|
| 404 |
+
"byteOffset": 26475520
|
| 405 |
+
}
|
| 406 |
+
],
|
| 407 |
+
"md5sum": "f53b583f02b20cdec88c289ac1360c67"
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"dataPath": "params_shard_10.bin",
|
| 411 |
+
"format": "raw-shard",
|
| 412 |
+
"nbytes": 39321600,
|
| 413 |
+
"records": [
|
| 414 |
+
{
|
| 415 |
+
"name": "transformer.h.16.mixer.Wqkv.weight",
|
| 416 |
+
"shape": [
|
| 417 |
+
7680,
|
| 418 |
+
2560
|
| 419 |
+
],
|
| 420 |
+
"dtype": "float16",
|
| 421 |
+
"format": "f32-to-bf16",
|
| 422 |
+
"nbytes": 39321600,
|
| 423 |
+
"byteOffset": 0
|
| 424 |
+
}
|
| 425 |
+
],
|
| 426 |
+
"md5sum": "1f2c12270558403bacbf455beac632f2"
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"dataPath": "params_shard_11.bin",
|
| 430 |
+
"format": "raw-shard",
|
| 431 |
+
"nbytes": 52428800,
|
| 432 |
+
"records": [
|
| 433 |
+
{
|
| 434 |
+
"name": "transformer.h.17.mlp.fc1.weight",
|
| 435 |
+
"shape": [
|
| 436 |
+
10240,
|
| 437 |
+
2560
|
| 438 |
+
],
|
| 439 |
+
"dtype": "float16",
|
| 440 |
+
"format": "f32-to-bf16",
|
| 441 |
+
"nbytes": 52428800,
|
| 442 |
+
"byteOffset": 0
|
| 443 |
+
}
|
| 444 |
+
],
|
| 445 |
+
"md5sum": "4f031084eb0520ba0155a8266460af39"
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"dataPath": "params_shard_12.bin",
|
| 449 |
+
"format": "raw-shard",
|
| 450 |
+
"nbytes": 52428800,
|
| 451 |
+
"records": [
|
| 452 |
+
{
|
| 453 |
+
"name": "transformer.h.17.mlp.fc2.weight",
|
| 454 |
+
"shape": [
|
| 455 |
+
2560,
|
| 456 |
+
10240
|
| 457 |
+
],
|
| 458 |
+
"dtype": "float16",
|
| 459 |
+
"format": "f32-to-bf16",
|
| 460 |
+
"nbytes": 52428800,
|
| 461 |
+
"byteOffset": 0
|
| 462 |
+
}
|
| 463 |
+
],
|
| 464 |
+
"md5sum": "1ec43d399b3b2c7a786a58842d7cc747"
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"dataPath": "params_shard_13.bin",
|
| 468 |
+
"format": "raw-shard",
|
| 469 |
+
"nbytes": 39321600,
|
| 470 |
+
"records": [
|
| 471 |
+
{
|
| 472 |
+
"name": "transformer.h.17.mixer.Wqkv.weight",
|
| 473 |
+
"shape": [
|
| 474 |
+
7680,
|
| 475 |
+
2560
|
| 476 |
+
],
|
| 477 |
+
"dtype": "float16",
|
| 478 |
+
"format": "f32-to-bf16",
|
| 479 |
+
"nbytes": 39321600,
|
| 480 |
+
"byteOffset": 0
|
| 481 |
+
}
|
| 482 |
+
],
|
| 483 |
+
"md5sum": "8d260f0b99188c3d223ab16d48d1c2bc"
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"dataPath": "params_shard_14.bin",
|
| 487 |
+
"format": "raw-shard",
|
| 488 |
+
"nbytes": 52428800,
|
| 489 |
+
"records": [
|
| 490 |
+
{
|
| 491 |
+
"name": "transformer.h.18.mlp.fc1.weight",
|
| 492 |
+
"shape": [
|
| 493 |
+
10240,
|
| 494 |
+
2560
|
| 495 |
+
],
|
| 496 |
+
"dtype": "float16",
|
| 497 |
+
"format": "f32-to-bf16",
|
| 498 |
+
"nbytes": 52428800,
|
| 499 |
+
"byteOffset": 0
|
| 500 |
+
}
|
| 501 |
+
],
|
| 502 |
+
"md5sum": "e2c988cf74aeb2ade3a874cb7c29d95c"
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"dataPath": "params_shard_15.bin",
|
| 506 |
+
"format": "raw-shard",
|
| 507 |
+
"nbytes": 52428800,
|
| 508 |
+
"records": [
|
| 509 |
+
{
|
| 510 |
+
"name": "transformer.h.18.mlp.fc2.weight",
|
| 511 |
+
"shape": [
|
| 512 |
+
2560,
|
| 513 |
+
10240
|
| 514 |
+
],
|
| 515 |
+
"dtype": "float16",
|
| 516 |
+
"format": "f32-to-bf16",
|
| 517 |
+
"nbytes": 52428800,
|
| 518 |
+
"byteOffset": 0
|
| 519 |
+
}
|
| 520 |
+
],
|
| 521 |
+
"md5sum": "5397e400be97efddd4b1e13600a0b70c"
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"dataPath": "params_shard_16.bin",
|
| 525 |
+
"format": "raw-shard",
|
| 526 |
+
"nbytes": 26327040,
|
| 527 |
+
"records": [
|
| 528 |
+
{
|
| 529 |
+
"name": "transformer.h.16.mixer.out_proj.weight",
|
| 530 |
+
"shape": [
|
| 531 |
+
2560,
|
| 532 |
+
2560
|
| 533 |
+
],
|
| 534 |
+
"dtype": "float16",
|
| 535 |
+
"format": "f32-to-bf16",
|
| 536 |
+
"nbytes": 13107200,
|
| 537 |
+
"byteOffset": 0
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"name": "transformer.h.16.mixer.Wqkv.bias",
|
| 541 |
+
"shape": [
|
| 542 |
+
7680
|
| 543 |
+
],
|
| 544 |
+
"dtype": "float16",
|
| 545 |
+
"format": "f32-to-bf16",
|
| 546 |
+
"nbytes": 15360,
|
| 547 |
+
"byteOffset": 13107200
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"name": "transformer.h.17.ln.bias",
|
| 551 |
+
"shape": [
|
| 552 |
+
2560
|
| 553 |
+
],
|
| 554 |
+
"dtype": "float16",
|
| 555 |
+
"format": "f32-to-bf16",
|
| 556 |
+
"nbytes": 5120,
|
| 557 |
+
"byteOffset": 13122560
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"name": "transformer.h.17.ln.weight",
|
| 561 |
+
"shape": [
|
| 562 |
+
2560
|
| 563 |
+
],
|
| 564 |
+
"dtype": "float16",
|
| 565 |
+
"format": "f32-to-bf16",
|
| 566 |
+
"nbytes": 5120,
|
| 567 |
+
"byteOffset": 13127680
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"name": "transformer.h.17.mlp.fc1.bias",
|
| 571 |
+
"shape": [
|
| 572 |
+
10240
|
| 573 |
+
],
|
| 574 |
+
"dtype": "float16",
|
| 575 |
+
"format": "f32-to-bf16",
|
| 576 |
+
"nbytes": 20480,
|
| 577 |
+
"byteOffset": 13132800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"name": "transformer.h.17.mlp.fc2.bias",
|
| 581 |
+
"shape": [
|
| 582 |
+
2560
|
| 583 |
+
],
|
| 584 |
+
"dtype": "float16",
|
| 585 |
+
"format": "f32-to-bf16",
|
| 586 |
+
"nbytes": 5120,
|
| 587 |
+
"byteOffset": 13153280
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"name": "transformer.h.17.mixer.out_proj.bias",
|
| 591 |
+
"shape": [
|
| 592 |
+
2560
|
| 593 |
+
],
|
| 594 |
+
"dtype": "float16",
|
| 595 |
+
"format": "f32-to-bf16",
|
| 596 |
+
"nbytes": 5120,
|
| 597 |
+
"byteOffset": 13158400
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"name": "transformer.h.17.mixer.out_proj.weight",
|
| 601 |
+
"shape": [
|
| 602 |
+
2560,
|
| 603 |
+
2560
|
| 604 |
+
],
|
| 605 |
+
"dtype": "float16",
|
| 606 |
+
"format": "f32-to-bf16",
|
| 607 |
+
"nbytes": 13107200,
|
| 608 |
+
"byteOffset": 13163520
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"name": "transformer.h.17.mixer.Wqkv.bias",
|
| 612 |
+
"shape": [
|
| 613 |
+
7680
|
| 614 |
+
],
|
| 615 |
+
"dtype": "float16",
|
| 616 |
+
"format": "f32-to-bf16",
|
| 617 |
+
"nbytes": 15360,
|
| 618 |
+
"byteOffset": 26270720
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"name": "transformer.h.18.ln.bias",
|
| 622 |
+
"shape": [
|
| 623 |
+
2560
|
| 624 |
+
],
|
| 625 |
+
"dtype": "float16",
|
| 626 |
+
"format": "f32-to-bf16",
|
| 627 |
+
"nbytes": 5120,
|
| 628 |
+
"byteOffset": 26286080
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"name": "transformer.h.18.ln.weight",
|
| 632 |
+
"shape": [
|
| 633 |
+
2560
|
| 634 |
+
],
|
| 635 |
+
"dtype": "float16",
|
| 636 |
+
"format": "f32-to-bf16",
|
| 637 |
+
"nbytes": 5120,
|
| 638 |
+
"byteOffset": 26291200
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"name": "transformer.h.18.mlp.fc1.bias",
|
| 642 |
+
"shape": [
|
| 643 |
+
10240
|
| 644 |
+
],
|
| 645 |
+
"dtype": "float16",
|
| 646 |
+
"format": "f32-to-bf16",
|
| 647 |
+
"nbytes": 20480,
|
| 648 |
+
"byteOffset": 26296320
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"name": "transformer.h.18.mlp.fc2.bias",
|
| 652 |
+
"shape": [
|
| 653 |
+
2560
|
| 654 |
+
],
|
| 655 |
+
"dtype": "float16",
|
| 656 |
+
"format": "f32-to-bf16",
|
| 657 |
+
"nbytes": 5120,
|
| 658 |
+
"byteOffset": 26316800
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"name": "transformer.h.18.mixer.out_proj.bias",
|
| 662 |
+
"shape": [
|
| 663 |
+
2560
|
| 664 |
+
],
|
| 665 |
+
"dtype": "float16",
|
| 666 |
+
"format": "f32-to-bf16",
|
| 667 |
+
"nbytes": 5120,
|
| 668 |
+
"byteOffset": 26321920
|
| 669 |
+
}
|
| 670 |
+
],
|
| 671 |
+
"md5sum": "f8a2d03403eb9e9cf7b9aa78181106b7"
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"dataPath": "params_shard_17.bin",
|
| 675 |
+
"format": "raw-shard",
|
| 676 |
+
"nbytes": 39321600,
|
| 677 |
+
"records": [
|
| 678 |
+
{
|
| 679 |
+
"name": "transformer.h.18.mixer.Wqkv.weight",
|
| 680 |
+
"shape": [
|
| 681 |
+
7680,
|
| 682 |
+
2560
|
| 683 |
+
],
|
| 684 |
+
"dtype": "float16",
|
| 685 |
+
"format": "f32-to-bf16",
|
| 686 |
+
"nbytes": 39321600,
|
| 687 |
+
"byteOffset": 0
|
| 688 |
+
}
|
| 689 |
+
],
|
| 690 |
+
"md5sum": "8f835d1be1a32e017fa3d6140eb46b44"
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"dataPath": "params_shard_18.bin",
|
| 694 |
+
"format": "raw-shard",
|
| 695 |
+
"nbytes": 52428800,
|
| 696 |
+
"records": [
|
| 697 |
+
{
|
| 698 |
+
"name": "transformer.h.19.mlp.fc1.weight",
|
| 699 |
+
"shape": [
|
| 700 |
+
10240,
|
| 701 |
+
2560
|
| 702 |
+
],
|
| 703 |
+
"dtype": "float16",
|
| 704 |
+
"format": "f32-to-bf16",
|
| 705 |
+
"nbytes": 52428800,
|
| 706 |
+
"byteOffset": 0
|
| 707 |
+
}
|
| 708 |
+
],
|
| 709 |
+
"md5sum": "eb1b239145a55d4c181f83ef0fed1959"
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"dataPath": "params_shard_19.bin",
|
| 713 |
+
"format": "raw-shard",
|
| 714 |
+
"nbytes": 52428800,
|
| 715 |
+
"records": [
|
| 716 |
+
{
|
| 717 |
+
"name": "transformer.h.19.mlp.fc2.weight",
|
| 718 |
+
"shape": [
|
| 719 |
+
2560,
|
| 720 |
+
10240
|
| 721 |
+
],
|
| 722 |
+
"dtype": "float16",
|
| 723 |
+
"format": "f32-to-bf16",
|
| 724 |
+
"nbytes": 52428800,
|
| 725 |
+
"byteOffset": 0
|
| 726 |
+
}
|
| 727 |
+
],
|
| 728 |
+
"md5sum": "1a2ebc4b8383975be62cb644e326db04"
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"dataPath": "params_shard_20.bin",
|
| 732 |
+
"format": "raw-shard",
|
| 733 |
+
"nbytes": 39321600,
|
| 734 |
+
"records": [
|
| 735 |
+
{
|
| 736 |
+
"name": "transformer.h.19.mixer.Wqkv.weight",
|
| 737 |
+
"shape": [
|
| 738 |
+
7680,
|
| 739 |
+
2560
|
| 740 |
+
],
|
| 741 |
+
"dtype": "float16",
|
| 742 |
+
"format": "f32-to-bf16",
|
| 743 |
+
"nbytes": 39321600,
|
| 744 |
+
"byteOffset": 0
|
| 745 |
+
}
|
| 746 |
+
],
|
| 747 |
+
"md5sum": "4dde6f985823ec281ab0ce5d2c2f4164"
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"dataPath": "params_shard_21.bin",
|
| 751 |
+
"format": "raw-shard",
|
| 752 |
+
"nbytes": 262144000,
|
| 753 |
+
"records": [
|
| 754 |
+
{
|
| 755 |
+
"name": "transformer.embd.weight",
|
| 756 |
+
"shape": [
|
| 757 |
+
51200,
|
| 758 |
+
2560
|
| 759 |
+
],
|
| 760 |
+
"dtype": "float16",
|
| 761 |
+
"format": "f32-to-bf16",
|
| 762 |
+
"nbytes": 262144000,
|
| 763 |
+
"byteOffset": 0
|
| 764 |
+
}
|
| 765 |
+
],
|
| 766 |
+
"md5sum": "8e80be24cbe7c82aa854016c3950729e"
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"dataPath": "params_shard_22.bin",
|
| 770 |
+
"format": "raw-shard",
|
| 771 |
+
"nbytes": 52428800,
|
| 772 |
+
"records": [
|
| 773 |
+
{
|
| 774 |
+
"name": "transformer.h.0.mlp.fc1.weight",
|
| 775 |
+
"shape": [
|
| 776 |
+
10240,
|
| 777 |
+
2560
|
| 778 |
+
],
|
| 779 |
+
"dtype": "float16",
|
| 780 |
+
"format": "f32-to-bf16",
|
| 781 |
+
"nbytes": 52428800,
|
| 782 |
+
"byteOffset": 0
|
| 783 |
+
}
|
| 784 |
+
],
|
| 785 |
+
"md5sum": "3cf77e681ad8fd29e0ce784823198e16"
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"dataPath": "params_shard_23.bin",
|
| 789 |
+
"format": "raw-shard",
|
| 790 |
+
"nbytes": 52428800,
|
| 791 |
+
"records": [
|
| 792 |
+
{
|
| 793 |
+
"name": "transformer.h.0.mlp.fc2.weight",
|
| 794 |
+
"shape": [
|
| 795 |
+
2560,
|
| 796 |
+
10240
|
| 797 |
+
],
|
| 798 |
+
"dtype": "float16",
|
| 799 |
+
"format": "f32-to-bf16",
|
| 800 |
+
"nbytes": 52428800,
|
| 801 |
+
"byteOffset": 0
|
| 802 |
+
}
|
| 803 |
+
],
|
| 804 |
+
"md5sum": "e20e12c7a3dca65da2f968dc73087129"
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"dataPath": "params_shard_24.bin",
|
| 808 |
+
"format": "raw-shard",
|
| 809 |
+
"nbytes": 26327040,
|
| 810 |
+
"records": [
|
| 811 |
+
{
|
| 812 |
+
"name": "transformer.h.18.mixer.out_proj.weight",
|
| 813 |
+
"shape": [
|
| 814 |
+
2560,
|
| 815 |
+
2560
|
| 816 |
+
],
|
| 817 |
+
"dtype": "float16",
|
| 818 |
+
"format": "f32-to-bf16",
|
| 819 |
+
"nbytes": 13107200,
|
| 820 |
+
"byteOffset": 0
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"name": "transformer.h.18.mixer.Wqkv.bias",
|
| 824 |
+
"shape": [
|
| 825 |
+
7680
|
| 826 |
+
],
|
| 827 |
+
"dtype": "float16",
|
| 828 |
+
"format": "f32-to-bf16",
|
| 829 |
+
"nbytes": 15360,
|
| 830 |
+
"byteOffset": 13107200
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"name": "transformer.h.19.ln.bias",
|
| 834 |
+
"shape": [
|
| 835 |
+
2560
|
| 836 |
+
],
|
| 837 |
+
"dtype": "float16",
|
| 838 |
+
"format": "f32-to-bf16",
|
| 839 |
+
"nbytes": 5120,
|
| 840 |
+
"byteOffset": 13122560
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"name": "transformer.h.19.ln.weight",
|
| 844 |
+
"shape": [
|
| 845 |
+
2560
|
| 846 |
+
],
|
| 847 |
+
"dtype": "float16",
|
| 848 |
+
"format": "f32-to-bf16",
|
| 849 |
+
"nbytes": 5120,
|
| 850 |
+
"byteOffset": 13127680
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"name": "transformer.h.19.mlp.fc1.bias",
|
| 854 |
+
"shape": [
|
| 855 |
+
10240
|
| 856 |
+
],
|
| 857 |
+
"dtype": "float16",
|
| 858 |
+
"format": "f32-to-bf16",
|
| 859 |
+
"nbytes": 20480,
|
| 860 |
+
"byteOffset": 13132800
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"name": "transformer.h.19.mlp.fc2.bias",
|
| 864 |
+
"shape": [
|
| 865 |
+
2560
|
| 866 |
+
],
|
| 867 |
+
"dtype": "float16",
|
| 868 |
+
"format": "f32-to-bf16",
|
| 869 |
+
"nbytes": 5120,
|
| 870 |
+
"byteOffset": 13153280
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"name": "transformer.h.19.mixer.out_proj.bias",
|
| 874 |
+
"shape": [
|
| 875 |
+
2560
|
| 876 |
+
],
|
| 877 |
+
"dtype": "float16",
|
| 878 |
+
"format": "f32-to-bf16",
|
| 879 |
+
"nbytes": 5120,
|
| 880 |
+
"byteOffset": 13158400
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"name": "transformer.h.19.mixer.out_proj.weight",
|
| 884 |
+
"shape": [
|
| 885 |
+
2560,
|
| 886 |
+
2560
|
| 887 |
+
],
|
| 888 |
+
"dtype": "float16",
|
| 889 |
+
"format": "f32-to-bf16",
|
| 890 |
+
"nbytes": 13107200,
|
| 891 |
+
"byteOffset": 13163520
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"name": "transformer.h.19.mixer.Wqkv.bias",
|
| 895 |
+
"shape": [
|
| 896 |
+
7680
|
| 897 |
+
],
|
| 898 |
+
"dtype": "float16",
|
| 899 |
+
"format": "f32-to-bf16",
|
| 900 |
+
"nbytes": 15360,
|
| 901 |
+
"byteOffset": 26270720
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"name": "transformer.h.0.ln.bias",
|
| 905 |
+
"shape": [
|
| 906 |
+
2560
|
| 907 |
+
],
|
| 908 |
+
"dtype": "float16",
|
| 909 |
+
"format": "f32-to-bf16",
|
| 910 |
+
"nbytes": 5120,
|
| 911 |
+
"byteOffset": 26286080
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"name": "transformer.h.0.ln.weight",
|
| 915 |
+
"shape": [
|
| 916 |
+
2560
|
| 917 |
+
],
|
| 918 |
+
"dtype": "float16",
|
| 919 |
+
"format": "f32-to-bf16",
|
| 920 |
+
"nbytes": 5120,
|
| 921 |
+
"byteOffset": 26291200
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"name": "transformer.h.0.mlp.fc1.bias",
|
| 925 |
+
"shape": [
|
| 926 |
+
10240
|
| 927 |
+
],
|
| 928 |
+
"dtype": "float16",
|
| 929 |
+
"format": "f32-to-bf16",
|
| 930 |
+
"nbytes": 20480,
|
| 931 |
+
"byteOffset": 26296320
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"name": "transformer.h.0.mlp.fc2.bias",
|
| 935 |
+
"shape": [
|
| 936 |
+
2560
|
| 937 |
+
],
|
| 938 |
+
"dtype": "float16",
|
| 939 |
+
"format": "f32-to-bf16",
|
| 940 |
+
"nbytes": 5120,
|
| 941 |
+
"byteOffset": 26316800
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"name": "transformer.h.0.mixer.out_proj.bias",
|
| 945 |
+
"shape": [
|
| 946 |
+
2560
|
| 947 |
+
],
|
| 948 |
+
"dtype": "float16",
|
| 949 |
+
"format": "f32-to-bf16",
|
| 950 |
+
"nbytes": 5120,
|
| 951 |
+
"byteOffset": 26321920
|
| 952 |
+
}
|
| 953 |
+
],
|
| 954 |
+
"md5sum": "9ac07740b35a8e13617dd0e709cb0d69"
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"dataPath": "params_shard_25.bin",
|
| 958 |
+
"format": "raw-shard",
|
| 959 |
+
"nbytes": 39321600,
|
| 960 |
+
"records": [
|
| 961 |
+
{
|
| 962 |
+
"name": "transformer.h.0.mixer.Wqkv.weight",
|
| 963 |
+
"shape": [
|
| 964 |
+
7680,
|
| 965 |
+
2560
|
| 966 |
+
],
|
| 967 |
+
"dtype": "float16",
|
| 968 |
+
"format": "f32-to-bf16",
|
| 969 |
+
"nbytes": 39321600,
|
| 970 |
+
"byteOffset": 0
|
| 971 |
+
}
|
| 972 |
+
],
|
| 973 |
+
"md5sum": "686131149665cc509ab60acbda61725a"
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"dataPath": "params_shard_26.bin",
|
| 977 |
+
"format": "raw-shard",
|
| 978 |
+
"nbytes": 52428800,
|
| 979 |
+
"records": [
|
| 980 |
+
{
|
| 981 |
+
"name": "transformer.h.1.mlp.fc1.weight",
|
| 982 |
+
"shape": [
|
| 983 |
+
10240,
|
| 984 |
+
2560
|
| 985 |
+
],
|
| 986 |
+
"dtype": "float16",
|
| 987 |
+
"format": "f32-to-bf16",
|
| 988 |
+
"nbytes": 52428800,
|
| 989 |
+
"byteOffset": 0
|
| 990 |
+
}
|
| 991 |
+
],
|
| 992 |
+
"md5sum": "7f924e11f5a49c3bdc4a18eaf7c49d5c"
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"dataPath": "params_shard_27.bin",
|
| 996 |
+
"format": "raw-shard",
|
| 997 |
+
"nbytes": 52428800,
|
| 998 |
+
"records": [
|
| 999 |
+
{
|
| 1000 |
+
"name": "transformer.h.1.mlp.fc2.weight",
|
| 1001 |
+
"shape": [
|
| 1002 |
+
2560,
|
| 1003 |
+
10240
|
| 1004 |
+
],
|
| 1005 |
+
"dtype": "float16",
|
| 1006 |
+
"format": "f32-to-bf16",
|
| 1007 |
+
"nbytes": 52428800,
|
| 1008 |
+
"byteOffset": 0
|
| 1009 |
+
}
|
| 1010 |
+
],
|
| 1011 |
+
"md5sum": "25acdddd77a14c825123007c8a8c0f37"
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"dataPath": "params_shard_28.bin",
|
| 1015 |
+
"format": "raw-shard",
|
| 1016 |
+
"nbytes": 39321600,
|
| 1017 |
+
"records": [
|
| 1018 |
+
{
|
| 1019 |
+
"name": "transformer.h.1.mixer.Wqkv.weight",
|
| 1020 |
+
"shape": [
|
| 1021 |
+
7680,
|
| 1022 |
+
2560
|
| 1023 |
+
],
|
| 1024 |
+
"dtype": "float16",
|
| 1025 |
+
"format": "f32-to-bf16",
|
| 1026 |
+
"nbytes": 39321600,
|
| 1027 |
+
"byteOffset": 0
|
| 1028 |
+
}
|
| 1029 |
+
],
|
| 1030 |
+
"md5sum": "8686cab0ddf07e2d37ac73ffc4eaed45"
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"dataPath": "params_shard_29.bin",
|
| 1034 |
+
"format": "raw-shard",
|
| 1035 |
+
"nbytes": 52428800,
|
| 1036 |
+
"records": [
|
| 1037 |
+
{
|
| 1038 |
+
"name": "transformer.h.10.mlp.fc1.weight",
|
| 1039 |
+
"shape": [
|
| 1040 |
+
10240,
|
| 1041 |
+
2560
|
| 1042 |
+
],
|
| 1043 |
+
"dtype": "float16",
|
| 1044 |
+
"format": "f32-to-bf16",
|
| 1045 |
+
"nbytes": 52428800,
|
| 1046 |
+
"byteOffset": 0
|
| 1047 |
+
}
|
| 1048 |
+
],
|
| 1049 |
+
"md5sum": "364369ce587148d62299cfe8a72b8770"
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"dataPath": "params_shard_30.bin",
|
| 1053 |
+
"format": "raw-shard",
|
| 1054 |
+
"nbytes": 52428800,
|
| 1055 |
+
"records": [
|
| 1056 |
+
{
|
| 1057 |
+
"name": "transformer.h.10.mlp.fc2.weight",
|
| 1058 |
+
"shape": [
|
| 1059 |
+
2560,
|
| 1060 |
+
10240
|
| 1061 |
+
],
|
| 1062 |
+
"dtype": "float16",
|
| 1063 |
+
"format": "f32-to-bf16",
|
| 1064 |
+
"nbytes": 52428800,
|
| 1065 |
+
"byteOffset": 0
|
| 1066 |
+
}
|
| 1067 |
+
],
|
| 1068 |
+
"md5sum": "04cfa745317707b5a3054a4a2c7e5616"
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"dataPath": "params_shard_31.bin",
|
| 1072 |
+
"format": "raw-shard",
|
| 1073 |
+
"nbytes": 26327040,
|
| 1074 |
+
"records": [
|
| 1075 |
+
{
|
| 1076 |
+
"name": "transformer.h.0.mixer.out_proj.weight",
|
| 1077 |
+
"shape": [
|
| 1078 |
+
2560,
|
| 1079 |
+
2560
|
| 1080 |
+
],
|
| 1081 |
+
"dtype": "float16",
|
| 1082 |
+
"format": "f32-to-bf16",
|
| 1083 |
+
"nbytes": 13107200,
|
| 1084 |
+
"byteOffset": 0
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"name": "transformer.h.0.mixer.Wqkv.bias",
|
| 1088 |
+
"shape": [
|
| 1089 |
+
7680
|
| 1090 |
+
],
|
| 1091 |
+
"dtype": "float16",
|
| 1092 |
+
"format": "f32-to-bf16",
|
| 1093 |
+
"nbytes": 15360,
|
| 1094 |
+
"byteOffset": 13107200
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"name": "transformer.h.1.ln.bias",
|
| 1098 |
+
"shape": [
|
| 1099 |
+
2560
|
| 1100 |
+
],
|
| 1101 |
+
"dtype": "float16",
|
| 1102 |
+
"format": "f32-to-bf16",
|
| 1103 |
+
"nbytes": 5120,
|
| 1104 |
+
"byteOffset": 13122560
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"name": "transformer.h.1.ln.weight",
|
| 1108 |
+
"shape": [
|
| 1109 |
+
2560
|
| 1110 |
+
],
|
| 1111 |
+
"dtype": "float16",
|
| 1112 |
+
"format": "f32-to-bf16",
|
| 1113 |
+
"nbytes": 5120,
|
| 1114 |
+
"byteOffset": 13127680
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"name": "transformer.h.1.mlp.fc1.bias",
|
| 1118 |
+
"shape": [
|
| 1119 |
+
10240
|
| 1120 |
+
],
|
| 1121 |
+
"dtype": "float16",
|
| 1122 |
+
"format": "f32-to-bf16",
|
| 1123 |
+
"nbytes": 20480,
|
| 1124 |
+
"byteOffset": 13132800
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"name": "transformer.h.1.mlp.fc2.bias",
|
| 1128 |
+
"shape": [
|
| 1129 |
+
2560
|
| 1130 |
+
],
|
| 1131 |
+
"dtype": "float16",
|
| 1132 |
+
"format": "f32-to-bf16",
|
| 1133 |
+
"nbytes": 5120,
|
| 1134 |
+
"byteOffset": 13153280
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"name": "transformer.h.1.mixer.out_proj.bias",
|
| 1138 |
+
"shape": [
|
| 1139 |
+
2560
|
| 1140 |
+
],
|
| 1141 |
+
"dtype": "float16",
|
| 1142 |
+
"format": "f32-to-bf16",
|
| 1143 |
+
"nbytes": 5120,
|
| 1144 |
+
"byteOffset": 13158400
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"name": "transformer.h.1.mixer.out_proj.weight",
|
| 1148 |
+
"shape": [
|
| 1149 |
+
2560,
|
| 1150 |
+
2560
|
| 1151 |
+
],
|
| 1152 |
+
"dtype": "float16",
|
| 1153 |
+
"format": "f32-to-bf16",
|
| 1154 |
+
"nbytes": 13107200,
|
| 1155 |
+
"byteOffset": 13163520
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"name": "transformer.h.1.mixer.Wqkv.bias",
|
| 1159 |
+
"shape": [
|
| 1160 |
+
7680
|
| 1161 |
+
],
|
| 1162 |
+
"dtype": "float16",
|
| 1163 |
+
"format": "f32-to-bf16",
|
| 1164 |
+
"nbytes": 15360,
|
| 1165 |
+
"byteOffset": 26270720
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"name": "transformer.h.10.ln.bias",
|
| 1169 |
+
"shape": [
|
| 1170 |
+
2560
|
| 1171 |
+
],
|
| 1172 |
+
"dtype": "float16",
|
| 1173 |
+
"format": "f32-to-bf16",
|
| 1174 |
+
"nbytes": 5120,
|
| 1175 |
+
"byteOffset": 26286080
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"name": "transformer.h.10.ln.weight",
|
| 1179 |
+
"shape": [
|
| 1180 |
+
2560
|
| 1181 |
+
],
|
| 1182 |
+
"dtype": "float16",
|
| 1183 |
+
"format": "f32-to-bf16",
|
| 1184 |
+
"nbytes": 5120,
|
| 1185 |
+
"byteOffset": 26291200
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"name": "transformer.h.10.mlp.fc1.bias",
|
| 1189 |
+
"shape": [
|
| 1190 |
+
10240
|
| 1191 |
+
],
|
| 1192 |
+
"dtype": "float16",
|
| 1193 |
+
"format": "f32-to-bf16",
|
| 1194 |
+
"nbytes": 20480,
|
| 1195 |
+
"byteOffset": 26296320
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"name": "transformer.h.10.mlp.fc2.bias",
|
| 1199 |
+
"shape": [
|
| 1200 |
+
2560
|
| 1201 |
+
],
|
| 1202 |
+
"dtype": "float16",
|
| 1203 |
+
"format": "f32-to-bf16",
|
| 1204 |
+
"nbytes": 5120,
|
| 1205 |
+
"byteOffset": 26316800
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"name": "transformer.h.10.mixer.out_proj.bias",
|
| 1209 |
+
"shape": [
|
| 1210 |
+
2560
|
| 1211 |
+
],
|
| 1212 |
+
"dtype": "float16",
|
| 1213 |
+
"format": "f32-to-bf16",
|
| 1214 |
+
"nbytes": 5120,
|
| 1215 |
+
"byteOffset": 26321920
|
| 1216 |
+
}
|
| 1217 |
+
],
|
| 1218 |
+
"md5sum": "f9ecd7131d396059066f14b928914dcf"
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"dataPath": "params_shard_32.bin",
|
| 1222 |
+
"format": "raw-shard",
|
| 1223 |
+
"nbytes": 39321600,
|
| 1224 |
+
"records": [
|
| 1225 |
+
{
|
| 1226 |
+
"name": "transformer.h.10.mixer.Wqkv.weight",
|
| 1227 |
+
"shape": [
|
| 1228 |
+
7680,
|
| 1229 |
+
2560
|
| 1230 |
+
],
|
| 1231 |
+
"dtype": "float16",
|
| 1232 |
+
"format": "f32-to-bf16",
|
| 1233 |
+
"nbytes": 39321600,
|
| 1234 |
+
"byteOffset": 0
|
| 1235 |
+
}
|
| 1236 |
+
],
|
| 1237 |
+
"md5sum": "7d90087370a2350e7ab1dacc145fe966"
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"dataPath": "params_shard_33.bin",
|
| 1241 |
+
"format": "raw-shard",
|
| 1242 |
+
"nbytes": 52428800,
|
| 1243 |
+
"records": [
|
| 1244 |
+
{
|
| 1245 |
+
"name": "transformer.h.11.mlp.fc1.weight",
|
| 1246 |
+
"shape": [
|
| 1247 |
+
10240,
|
| 1248 |
+
2560
|
| 1249 |
+
],
|
| 1250 |
+
"dtype": "float16",
|
| 1251 |
+
"format": "f32-to-bf16",
|
| 1252 |
+
"nbytes": 52428800,
|
| 1253 |
+
"byteOffset": 0
|
| 1254 |
+
}
|
| 1255 |
+
],
|
| 1256 |
+
"md5sum": "bba2afa39105559b6abbd88707220870"
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"dataPath": "params_shard_34.bin",
|
| 1260 |
+
"format": "raw-shard",
|
| 1261 |
+
"nbytes": 52428800,
|
| 1262 |
+
"records": [
|
| 1263 |
+
{
|
| 1264 |
+
"name": "transformer.h.11.mlp.fc2.weight",
|
| 1265 |
+
"shape": [
|
| 1266 |
+
2560,
|
| 1267 |
+
10240
|
| 1268 |
+
],
|
| 1269 |
+
"dtype": "float16",
|
| 1270 |
+
"format": "f32-to-bf16",
|
| 1271 |
+
"nbytes": 52428800,
|
| 1272 |
+
"byteOffset": 0
|
| 1273 |
+
}
|
| 1274 |
+
],
|
| 1275 |
+
"md5sum": "13bca4c465f23d066f8166398373c9fe"
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"dataPath": "params_shard_35.bin",
|
| 1279 |
+
"format": "raw-shard",
|
| 1280 |
+
"nbytes": 39321600,
|
| 1281 |
+
"records": [
|
| 1282 |
+
{
|
| 1283 |
+
"name": "transformer.h.11.mixer.Wqkv.weight",
|
| 1284 |
+
"shape": [
|
| 1285 |
+
7680,
|
| 1286 |
+
2560
|
| 1287 |
+
],
|
| 1288 |
+
"dtype": "float16",
|
| 1289 |
+
"format": "f32-to-bf16",
|
| 1290 |
+
"nbytes": 39321600,
|
| 1291 |
+
"byteOffset": 0
|
| 1292 |
+
}
|
| 1293 |
+
],
|
| 1294 |
+
"md5sum": "0d47f892b7c1e0ee1a3573d62a4e3dce"
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"dataPath": "params_shard_36.bin",
|
| 1298 |
+
"format": "raw-shard",
|
| 1299 |
+
"nbytes": 52428800,
|
| 1300 |
+
"records": [
|
| 1301 |
+
{
|
| 1302 |
+
"name": "transformer.h.12.mlp.fc1.weight",
|
| 1303 |
+
"shape": [
|
| 1304 |
+
10240,
|
| 1305 |
+
2560
|
| 1306 |
+
],
|
| 1307 |
+
"dtype": "float16",
|
| 1308 |
+
"format": "f32-to-bf16",
|
| 1309 |
+
"nbytes": 52428800,
|
| 1310 |
+
"byteOffset": 0
|
| 1311 |
+
}
|
| 1312 |
+
],
|
| 1313 |
+
"md5sum": "d3e5a7817c7bf9c81ed43f7cd2e1a82d"
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"dataPath": "params_shard_37.bin",
|
| 1317 |
+
"format": "raw-shard",
|
| 1318 |
+
"nbytes": 52428800,
|
| 1319 |
+
"records": [
|
| 1320 |
+
{
|
| 1321 |
+
"name": "transformer.h.12.mlp.fc2.weight",
|
| 1322 |
+
"shape": [
|
| 1323 |
+
2560,
|
| 1324 |
+
10240
|
| 1325 |
+
],
|
| 1326 |
+
"dtype": "float16",
|
| 1327 |
+
"format": "f32-to-bf16",
|
| 1328 |
+
"nbytes": 52428800,
|
| 1329 |
+
"byteOffset": 0
|
| 1330 |
+
}
|
| 1331 |
+
],
|
| 1332 |
+
"md5sum": "b457f920d75e816966f9c05eefa2beb9"
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"dataPath": "params_shard_38.bin",
|
| 1336 |
+
"format": "raw-shard",
|
| 1337 |
+
"nbytes": 26327040,
|
| 1338 |
+
"records": [
|
| 1339 |
+
{
|
| 1340 |
+
"name": "transformer.h.10.mixer.out_proj.weight",
|
| 1341 |
+
"shape": [
|
| 1342 |
+
2560,
|
| 1343 |
+
2560
|
| 1344 |
+
],
|
| 1345 |
+
"dtype": "float16",
|
| 1346 |
+
"format": "f32-to-bf16",
|
| 1347 |
+
"nbytes": 13107200,
|
| 1348 |
+
"byteOffset": 0
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"name": "transformer.h.10.mixer.Wqkv.bias",
|
| 1352 |
+
"shape": [
|
| 1353 |
+
7680
|
| 1354 |
+
],
|
| 1355 |
+
"dtype": "float16",
|
| 1356 |
+
"format": "f32-to-bf16",
|
| 1357 |
+
"nbytes": 15360,
|
| 1358 |
+
"byteOffset": 13107200
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"name": "transformer.h.11.ln.bias",
|
| 1362 |
+
"shape": [
|
| 1363 |
+
2560
|
| 1364 |
+
],
|
| 1365 |
+
"dtype": "float16",
|
| 1366 |
+
"format": "f32-to-bf16",
|
| 1367 |
+
"nbytes": 5120,
|
| 1368 |
+
"byteOffset": 13122560
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"name": "transformer.h.11.ln.weight",
|
| 1372 |
+
"shape": [
|
| 1373 |
+
2560
|
| 1374 |
+
],
|
| 1375 |
+
"dtype": "float16",
|
| 1376 |
+
"format": "f32-to-bf16",
|
| 1377 |
+
"nbytes": 5120,
|
| 1378 |
+
"byteOffset": 13127680
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"name": "transformer.h.11.mlp.fc1.bias",
|
| 1382 |
+
"shape": [
|
| 1383 |
+
10240
|
| 1384 |
+
],
|
| 1385 |
+
"dtype": "float16",
|
| 1386 |
+
"format": "f32-to-bf16",
|
| 1387 |
+
"nbytes": 20480,
|
| 1388 |
+
"byteOffset": 13132800
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"name": "transformer.h.11.mlp.fc2.bias",
|
| 1392 |
+
"shape": [
|
| 1393 |
+
2560
|
| 1394 |
+
],
|
| 1395 |
+
"dtype": "float16",
|
| 1396 |
+
"format": "f32-to-bf16",
|
| 1397 |
+
"nbytes": 5120,
|
| 1398 |
+
"byteOffset": 13153280
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"name": "transformer.h.11.mixer.out_proj.bias",
|
| 1402 |
+
"shape": [
|
| 1403 |
+
2560
|
| 1404 |
+
],
|
| 1405 |
+
"dtype": "float16",
|
| 1406 |
+
"format": "f32-to-bf16",
|
| 1407 |
+
"nbytes": 5120,
|
| 1408 |
+
"byteOffset": 13158400
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"name": "transformer.h.11.mixer.out_proj.weight",
|
| 1412 |
+
"shape": [
|
| 1413 |
+
2560,
|
| 1414 |
+
2560
|
| 1415 |
+
],
|
| 1416 |
+
"dtype": "float16",
|
| 1417 |
+
"format": "f32-to-bf16",
|
| 1418 |
+
"nbytes": 13107200,
|
| 1419 |
+
"byteOffset": 13163520
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"name": "transformer.h.11.mixer.Wqkv.bias",
|
| 1423 |
+
"shape": [
|
| 1424 |
+
7680
|
| 1425 |
+
],
|
| 1426 |
+
"dtype": "float16",
|
| 1427 |
+
"format": "f32-to-bf16",
|
| 1428 |
+
"nbytes": 15360,
|
| 1429 |
+
"byteOffset": 26270720
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"name": "transformer.h.12.ln.bias",
|
| 1433 |
+
"shape": [
|
| 1434 |
+
2560
|
| 1435 |
+
],
|
| 1436 |
+
"dtype": "float16",
|
| 1437 |
+
"format": "f32-to-bf16",
|
| 1438 |
+
"nbytes": 5120,
|
| 1439 |
+
"byteOffset": 26286080
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"name": "transformer.h.12.ln.weight",
|
| 1443 |
+
"shape": [
|
| 1444 |
+
2560
|
| 1445 |
+
],
|
| 1446 |
+
"dtype": "float16",
|
| 1447 |
+
"format": "f32-to-bf16",
|
| 1448 |
+
"nbytes": 5120,
|
| 1449 |
+
"byteOffset": 26291200
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"name": "transformer.h.12.mlp.fc1.bias",
|
| 1453 |
+
"shape": [
|
| 1454 |
+
10240
|
| 1455 |
+
],
|
| 1456 |
+
"dtype": "float16",
|
| 1457 |
+
"format": "f32-to-bf16",
|
| 1458 |
+
"nbytes": 20480,
|
| 1459 |
+
"byteOffset": 26296320
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"name": "transformer.h.12.mlp.fc2.bias",
|
| 1463 |
+
"shape": [
|
| 1464 |
+
2560
|
| 1465 |
+
],
|
| 1466 |
+
"dtype": "float16",
|
| 1467 |
+
"format": "f32-to-bf16",
|
| 1468 |
+
"nbytes": 5120,
|
| 1469 |
+
"byteOffset": 26316800
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"name": "transformer.h.12.mixer.out_proj.bias",
|
| 1473 |
+
"shape": [
|
| 1474 |
+
2560
|
| 1475 |
+
],
|
| 1476 |
+
"dtype": "float16",
|
| 1477 |
+
"format": "f32-to-bf16",
|
| 1478 |
+
"nbytes": 5120,
|
| 1479 |
+
"byteOffset": 26321920
|
| 1480 |
+
}
|
| 1481 |
+
],
|
| 1482 |
+
"md5sum": "f232fe0a5e8b69aaf51f286cf9fd1f43"
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"dataPath": "params_shard_39.bin",
|
| 1486 |
+
"format": "raw-shard",
|
| 1487 |
+
"nbytes": 39321600,
|
| 1488 |
+
"records": [
|
| 1489 |
+
{
|
| 1490 |
+
"name": "transformer.h.12.mixer.Wqkv.weight",
|
| 1491 |
+
"shape": [
|
| 1492 |
+
7680,
|
| 1493 |
+
2560
|
| 1494 |
+
],
|
| 1495 |
+
"dtype": "float16",
|
| 1496 |
+
"format": "f32-to-bf16",
|
| 1497 |
+
"nbytes": 39321600,
|
| 1498 |
+
"byteOffset": 0
|
| 1499 |
+
}
|
| 1500 |
+
],
|
| 1501 |
+
"md5sum": "5837435a6f54fce26919f36840d2564e"
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"dataPath": "params_shard_40.bin",
|
| 1505 |
+
"format": "raw-shard",
|
| 1506 |
+
"nbytes": 52428800,
|
| 1507 |
+
"records": [
|
| 1508 |
+
{
|
| 1509 |
+
"name": "transformer.h.13.mlp.fc1.weight",
|
| 1510 |
+
"shape": [
|
| 1511 |
+
10240,
|
| 1512 |
+
2560
|
| 1513 |
+
],
|
| 1514 |
+
"dtype": "float16",
|
| 1515 |
+
"format": "f32-to-bf16",
|
| 1516 |
+
"nbytes": 52428800,
|
| 1517 |
+
"byteOffset": 0
|
| 1518 |
+
}
|
| 1519 |
+
],
|
| 1520 |
+
"md5sum": "6f5c0f70857a2dc5c3a0e3ed0d8593f3"
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"dataPath": "params_shard_41.bin",
|
| 1524 |
+
"format": "raw-shard",
|
| 1525 |
+
"nbytes": 52428800,
|
| 1526 |
+
"records": [
|
| 1527 |
+
{
|
| 1528 |
+
"name": "transformer.h.13.mlp.fc2.weight",
|
| 1529 |
+
"shape": [
|
| 1530 |
+
2560,
|
| 1531 |
+
10240
|
| 1532 |
+
],
|
| 1533 |
+
"dtype": "float16",
|
| 1534 |
+
"format": "f32-to-bf16",
|
| 1535 |
+
"nbytes": 52428800,
|
| 1536 |
+
"byteOffset": 0
|
| 1537 |
+
}
|
| 1538 |
+
],
|
| 1539 |
+
"md5sum": "3663f5adfd843eac31a20342a6e4f578"
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"dataPath": "params_shard_42.bin",
|
| 1543 |
+
"format": "raw-shard",
|
| 1544 |
+
"nbytes": 39321600,
|
| 1545 |
+
"records": [
|
| 1546 |
+
{
|
| 1547 |
+
"name": "transformer.h.13.mixer.Wqkv.weight",
|
| 1548 |
+
"shape": [
|
| 1549 |
+
7680,
|
| 1550 |
+
2560
|
| 1551 |
+
],
|
| 1552 |
+
"dtype": "float16",
|
| 1553 |
+
"format": "f32-to-bf16",
|
| 1554 |
+
"nbytes": 39321600,
|
| 1555 |
+
"byteOffset": 0
|
| 1556 |
+
}
|
| 1557 |
+
],
|
| 1558 |
+
"md5sum": "66549463b0931dc08db16a65ebfcef58"
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"dataPath": "params_shard_43.bin",
|
| 1562 |
+
"format": "raw-shard",
|
| 1563 |
+
"nbytes": 52428800,
|
| 1564 |
+
"records": [
|
| 1565 |
+
{
|
| 1566 |
+
"name": "transformer.h.2.mlp.fc1.weight",
|
| 1567 |
+
"shape": [
|
| 1568 |
+
10240,
|
| 1569 |
+
2560
|
| 1570 |
+
],
|
| 1571 |
+
"dtype": "float16",
|
| 1572 |
+
"format": "f32-to-bf16",
|
| 1573 |
+
"nbytes": 52428800,
|
| 1574 |
+
"byteOffset": 0
|
| 1575 |
+
}
|
| 1576 |
+
],
|
| 1577 |
+
"md5sum": "5dc9124d2ddfca57b608a85e630c1d05"
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"dataPath": "params_shard_44.bin",
|
| 1581 |
+
"format": "raw-shard",
|
| 1582 |
+
"nbytes": 52428800,
|
| 1583 |
+
"records": [
|
| 1584 |
+
{
|
| 1585 |
+
"name": "transformer.h.2.mlp.fc2.weight",
|
| 1586 |
+
"shape": [
|
| 1587 |
+
2560,
|
| 1588 |
+
10240
|
| 1589 |
+
],
|
| 1590 |
+
"dtype": "float16",
|
| 1591 |
+
"format": "f32-to-bf16",
|
| 1592 |
+
"nbytes": 52428800,
|
| 1593 |
+
"byteOffset": 0
|
| 1594 |
+
}
|
| 1595 |
+
],
|
| 1596 |
+
"md5sum": "508d927411c8164c5c61e311480ad498"
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"dataPath": "params_shard_45.bin",
|
| 1600 |
+
"format": "raw-shard",
|
| 1601 |
+
"nbytes": 26327040,
|
| 1602 |
+
"records": [
|
| 1603 |
+
{
|
| 1604 |
+
"name": "transformer.h.12.mixer.out_proj.weight",
|
| 1605 |
+
"shape": [
|
| 1606 |
+
2560,
|
| 1607 |
+
2560
|
| 1608 |
+
],
|
| 1609 |
+
"dtype": "float16",
|
| 1610 |
+
"format": "f32-to-bf16",
|
| 1611 |
+
"nbytes": 13107200,
|
| 1612 |
+
"byteOffset": 0
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"name": "transformer.h.12.mixer.Wqkv.bias",
|
| 1616 |
+
"shape": [
|
| 1617 |
+
7680
|
| 1618 |
+
],
|
| 1619 |
+
"dtype": "float16",
|
| 1620 |
+
"format": "f32-to-bf16",
|
| 1621 |
+
"nbytes": 15360,
|
| 1622 |
+
"byteOffset": 13107200
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"name": "transformer.h.13.ln.bias",
|
| 1626 |
+
"shape": [
|
| 1627 |
+
2560
|
| 1628 |
+
],
|
| 1629 |
+
"dtype": "float16",
|
| 1630 |
+
"format": "f32-to-bf16",
|
| 1631 |
+
"nbytes": 5120,
|
| 1632 |
+
"byteOffset": 13122560
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"name": "transformer.h.13.ln.weight",
|
| 1636 |
+
"shape": [
|
| 1637 |
+
2560
|
| 1638 |
+
],
|
| 1639 |
+
"dtype": "float16",
|
| 1640 |
+
"format": "f32-to-bf16",
|
| 1641 |
+
"nbytes": 5120,
|
| 1642 |
+
"byteOffset": 13127680
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"name": "transformer.h.13.mlp.fc1.bias",
|
| 1646 |
+
"shape": [
|
| 1647 |
+
10240
|
| 1648 |
+
],
|
| 1649 |
+
"dtype": "float16",
|
| 1650 |
+
"format": "f32-to-bf16",
|
| 1651 |
+
"nbytes": 20480,
|
| 1652 |
+
"byteOffset": 13132800
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"name": "transformer.h.13.mlp.fc2.bias",
|
| 1656 |
+
"shape": [
|
| 1657 |
+
2560
|
| 1658 |
+
],
|
| 1659 |
+
"dtype": "float16",
|
| 1660 |
+
"format": "f32-to-bf16",
|
| 1661 |
+
"nbytes": 5120,
|
| 1662 |
+
"byteOffset": 13153280
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"name": "transformer.h.13.mixer.out_proj.bias",
|
| 1666 |
+
"shape": [
|
| 1667 |
+
2560
|
| 1668 |
+
],
|
| 1669 |
+
"dtype": "float16",
|
| 1670 |
+
"format": "f32-to-bf16",
|
| 1671 |
+
"nbytes": 5120,
|
| 1672 |
+
"byteOffset": 13158400
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"name": "transformer.h.13.mixer.out_proj.weight",
|
| 1676 |
+
"shape": [
|
| 1677 |
+
2560,
|
| 1678 |
+
2560
|
| 1679 |
+
],
|
| 1680 |
+
"dtype": "float16",
|
| 1681 |
+
"format": "f32-to-bf16",
|
| 1682 |
+
"nbytes": 13107200,
|
| 1683 |
+
"byteOffset": 13163520
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"name": "transformer.h.13.mixer.Wqkv.bias",
|
| 1687 |
+
"shape": [
|
| 1688 |
+
7680
|
| 1689 |
+
],
|
| 1690 |
+
"dtype": "float16",
|
| 1691 |
+
"format": "f32-to-bf16",
|
| 1692 |
+
"nbytes": 15360,
|
| 1693 |
+
"byteOffset": 26270720
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"name": "transformer.h.2.ln.bias",
|
| 1697 |
+
"shape": [
|
| 1698 |
+
2560
|
| 1699 |
+
],
|
| 1700 |
+
"dtype": "float16",
|
| 1701 |
+
"format": "f32-to-bf16",
|
| 1702 |
+
"nbytes": 5120,
|
| 1703 |
+
"byteOffset": 26286080
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"name": "transformer.h.2.ln.weight",
|
| 1707 |
+
"shape": [
|
| 1708 |
+
2560
|
| 1709 |
+
],
|
| 1710 |
+
"dtype": "float16",
|
| 1711 |
+
"format": "f32-to-bf16",
|
| 1712 |
+
"nbytes": 5120,
|
| 1713 |
+
"byteOffset": 26291200
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"name": "transformer.h.2.mlp.fc1.bias",
|
| 1717 |
+
"shape": [
|
| 1718 |
+
10240
|
| 1719 |
+
],
|
| 1720 |
+
"dtype": "float16",
|
| 1721 |
+
"format": "f32-to-bf16",
|
| 1722 |
+
"nbytes": 20480,
|
| 1723 |
+
"byteOffset": 26296320
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"name": "transformer.h.2.mlp.fc2.bias",
|
| 1727 |
+
"shape": [
|
| 1728 |
+
2560
|
| 1729 |
+
],
|
| 1730 |
+
"dtype": "float16",
|
| 1731 |
+
"format": "f32-to-bf16",
|
| 1732 |
+
"nbytes": 5120,
|
| 1733 |
+
"byteOffset": 26316800
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"name": "transformer.h.2.mixer.out_proj.bias",
|
| 1737 |
+
"shape": [
|
| 1738 |
+
2560
|
| 1739 |
+
],
|
| 1740 |
+
"dtype": "float16",
|
| 1741 |
+
"format": "f32-to-bf16",
|
| 1742 |
+
"nbytes": 5120,
|
| 1743 |
+
"byteOffset": 26321920
|
| 1744 |
+
}
|
| 1745 |
+
],
|
| 1746 |
+
"md5sum": "30e056b33c457e301b54e9028e4e3b7c"
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"dataPath": "params_shard_46.bin",
|
| 1750 |
+
"format": "raw-shard",
|
| 1751 |
+
"nbytes": 39321600,
|
| 1752 |
+
"records": [
|
| 1753 |
+
{
|
| 1754 |
+
"name": "transformer.h.2.mixer.Wqkv.weight",
|
| 1755 |
+
"shape": [
|
| 1756 |
+
7680,
|
| 1757 |
+
2560
|
| 1758 |
+
],
|
| 1759 |
+
"dtype": "float16",
|
| 1760 |
+
"format": "f32-to-bf16",
|
| 1761 |
+
"nbytes": 39321600,
|
| 1762 |
+
"byteOffset": 0
|
| 1763 |
+
}
|
| 1764 |
+
],
|
| 1765 |
+
"md5sum": "02183b8cfd0913fb062d44f6dc7bb435"
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"dataPath": "params_shard_47.bin",
|
| 1769 |
+
"format": "raw-shard",
|
| 1770 |
+
"nbytes": 52428800,
|
| 1771 |
+
"records": [
|
| 1772 |
+
{
|
| 1773 |
+
"name": "transformer.h.3.mlp.fc1.weight",
|
| 1774 |
+
"shape": [
|
| 1775 |
+
10240,
|
| 1776 |
+
2560
|
| 1777 |
+
],
|
| 1778 |
+
"dtype": "float16",
|
| 1779 |
+
"format": "f32-to-bf16",
|
| 1780 |
+
"nbytes": 52428800,
|
| 1781 |
+
"byteOffset": 0
|
| 1782 |
+
}
|
| 1783 |
+
],
|
| 1784 |
+
"md5sum": "c19fd2b41ca5d52e9b1f56210ba8d3d8"
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"dataPath": "params_shard_48.bin",
|
| 1788 |
+
"format": "raw-shard",
|
| 1789 |
+
"nbytes": 52428800,
|
| 1790 |
+
"records": [
|
| 1791 |
+
{
|
| 1792 |
+
"name": "transformer.h.3.mlp.fc2.weight",
|
| 1793 |
+
"shape": [
|
| 1794 |
+
2560,
|
| 1795 |
+
10240
|
| 1796 |
+
],
|
| 1797 |
+
"dtype": "float16",
|
| 1798 |
+
"format": "f32-to-bf16",
|
| 1799 |
+
"nbytes": 52428800,
|
| 1800 |
+
"byteOffset": 0
|
| 1801 |
+
}
|
| 1802 |
+
],
|
| 1803 |
+
"md5sum": "aa7ef0fe99061caae303a69488f71e76"
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"dataPath": "params_shard_49.bin",
|
| 1807 |
+
"format": "raw-shard",
|
| 1808 |
+
"nbytes": 39321600,
|
| 1809 |
+
"records": [
|
| 1810 |
+
{
|
| 1811 |
+
"name": "transformer.h.3.mixer.Wqkv.weight",
|
| 1812 |
+
"shape": [
|
| 1813 |
+
7680,
|
| 1814 |
+
2560
|
| 1815 |
+
],
|
| 1816 |
+
"dtype": "float16",
|
| 1817 |
+
"format": "f32-to-bf16",
|
| 1818 |
+
"nbytes": 39321600,
|
| 1819 |
+
"byteOffset": 0
|
| 1820 |
+
}
|
| 1821 |
+
],
|
| 1822 |
+
"md5sum": "03886d58a911935275e3ade03254936c"
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"dataPath": "params_shard_50.bin",
|
| 1826 |
+
"format": "raw-shard",
|
| 1827 |
+
"nbytes": 52428800,
|
| 1828 |
+
"records": [
|
| 1829 |
+
{
|
| 1830 |
+
"name": "transformer.h.4.mlp.fc1.weight",
|
| 1831 |
+
"shape": [
|
| 1832 |
+
10240,
|
| 1833 |
+
2560
|
| 1834 |
+
],
|
| 1835 |
+
"dtype": "float16",
|
| 1836 |
+
"format": "f32-to-bf16",
|
| 1837 |
+
"nbytes": 52428800,
|
| 1838 |
+
"byteOffset": 0
|
| 1839 |
+
}
|
| 1840 |
+
],
|
| 1841 |
+
"md5sum": "992123d9456fe73af283b58198c3a8fe"
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"dataPath": "params_shard_51.bin",
|
| 1845 |
+
"format": "raw-shard",
|
| 1846 |
+
"nbytes": 52428800,
|
| 1847 |
+
"records": [
|
| 1848 |
+
{
|
| 1849 |
+
"name": "transformer.h.4.mlp.fc2.weight",
|
| 1850 |
+
"shape": [
|
| 1851 |
+
2560,
|
| 1852 |
+
10240
|
| 1853 |
+
],
|
| 1854 |
+
"dtype": "float16",
|
| 1855 |
+
"format": "f32-to-bf16",
|
| 1856 |
+
"nbytes": 52428800,
|
| 1857 |
+
"byteOffset": 0
|
| 1858 |
+
}
|
| 1859 |
+
],
|
| 1860 |
+
"md5sum": "2f1ee0816f479dfd634dcfab091e095d"
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"dataPath": "params_shard_52.bin",
|
| 1864 |
+
"format": "raw-shard",
|
| 1865 |
+
"nbytes": 26327040,
|
| 1866 |
+
"records": [
|
| 1867 |
+
{
|
| 1868 |
+
"name": "transformer.h.2.mixer.out_proj.weight",
|
| 1869 |
+
"shape": [
|
| 1870 |
+
2560,
|
| 1871 |
+
2560
|
| 1872 |
+
],
|
| 1873 |
+
"dtype": "float16",
|
| 1874 |
+
"format": "f32-to-bf16",
|
| 1875 |
+
"nbytes": 13107200,
|
| 1876 |
+
"byteOffset": 0
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"name": "transformer.h.2.mixer.Wqkv.bias",
|
| 1880 |
+
"shape": [
|
| 1881 |
+
7680
|
| 1882 |
+
],
|
| 1883 |
+
"dtype": "float16",
|
| 1884 |
+
"format": "f32-to-bf16",
|
| 1885 |
+
"nbytes": 15360,
|
| 1886 |
+
"byteOffset": 13107200
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"name": "transformer.h.3.ln.bias",
|
| 1890 |
+
"shape": [
|
| 1891 |
+
2560
|
| 1892 |
+
],
|
| 1893 |
+
"dtype": "float16",
|
| 1894 |
+
"format": "f32-to-bf16",
|
| 1895 |
+
"nbytes": 5120,
|
| 1896 |
+
"byteOffset": 13122560
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"name": "transformer.h.3.ln.weight",
|
| 1900 |
+
"shape": [
|
| 1901 |
+
2560
|
| 1902 |
+
],
|
| 1903 |
+
"dtype": "float16",
|
| 1904 |
+
"format": "f32-to-bf16",
|
| 1905 |
+
"nbytes": 5120,
|
| 1906 |
+
"byteOffset": 13127680
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"name": "transformer.h.3.mlp.fc1.bias",
|
| 1910 |
+
"shape": [
|
| 1911 |
+
10240
|
| 1912 |
+
],
|
| 1913 |
+
"dtype": "float16",
|
| 1914 |
+
"format": "f32-to-bf16",
|
| 1915 |
+
"nbytes": 20480,
|
| 1916 |
+
"byteOffset": 13132800
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"name": "transformer.h.3.mlp.fc2.bias",
|
| 1920 |
+
"shape": [
|
| 1921 |
+
2560
|
| 1922 |
+
],
|
| 1923 |
+
"dtype": "float16",
|
| 1924 |
+
"format": "f32-to-bf16",
|
| 1925 |
+
"nbytes": 5120,
|
| 1926 |
+
"byteOffset": 13153280
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"name": "transformer.h.3.mixer.out_proj.bias",
|
| 1930 |
+
"shape": [
|
| 1931 |
+
2560
|
| 1932 |
+
],
|
| 1933 |
+
"dtype": "float16",
|
| 1934 |
+
"format": "f32-to-bf16",
|
| 1935 |
+
"nbytes": 5120,
|
| 1936 |
+
"byteOffset": 13158400
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"name": "transformer.h.3.mixer.out_proj.weight",
|
| 1940 |
+
"shape": [
|
| 1941 |
+
2560,
|
| 1942 |
+
2560
|
| 1943 |
+
],
|
| 1944 |
+
"dtype": "float16",
|
| 1945 |
+
"format": "f32-to-bf16",
|
| 1946 |
+
"nbytes": 13107200,
|
| 1947 |
+
"byteOffset": 13163520
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"name": "transformer.h.3.mixer.Wqkv.bias",
|
| 1951 |
+
"shape": [
|
| 1952 |
+
7680
|
| 1953 |
+
],
|
| 1954 |
+
"dtype": "float16",
|
| 1955 |
+
"format": "f32-to-bf16",
|
| 1956 |
+
"nbytes": 15360,
|
| 1957 |
+
"byteOffset": 26270720
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"name": "transformer.h.4.ln.bias",
|
| 1961 |
+
"shape": [
|
| 1962 |
+
2560
|
| 1963 |
+
],
|
| 1964 |
+
"dtype": "float16",
|
| 1965 |
+
"format": "f32-to-bf16",
|
| 1966 |
+
"nbytes": 5120,
|
| 1967 |
+
"byteOffset": 26286080
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"name": "transformer.h.4.ln.weight",
|
| 1971 |
+
"shape": [
|
| 1972 |
+
2560
|
| 1973 |
+
],
|
| 1974 |
+
"dtype": "float16",
|
| 1975 |
+
"format": "f32-to-bf16",
|
| 1976 |
+
"nbytes": 5120,
|
| 1977 |
+
"byteOffset": 26291200
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"name": "transformer.h.4.mlp.fc1.bias",
|
| 1981 |
+
"shape": [
|
| 1982 |
+
10240
|
| 1983 |
+
],
|
| 1984 |
+
"dtype": "float16",
|
| 1985 |
+
"format": "f32-to-bf16",
|
| 1986 |
+
"nbytes": 20480,
|
| 1987 |
+
"byteOffset": 26296320
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"name": "transformer.h.4.mlp.fc2.bias",
|
| 1991 |
+
"shape": [
|
| 1992 |
+
2560
|
| 1993 |
+
],
|
| 1994 |
+
"dtype": "float16",
|
| 1995 |
+
"format": "f32-to-bf16",
|
| 1996 |
+
"nbytes": 5120,
|
| 1997 |
+
"byteOffset": 26316800
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"name": "transformer.h.4.mixer.out_proj.bias",
|
| 2001 |
+
"shape": [
|
| 2002 |
+
2560
|
| 2003 |
+
],
|
| 2004 |
+
"dtype": "float16",
|
| 2005 |
+
"format": "f32-to-bf16",
|
| 2006 |
+
"nbytes": 5120,
|
| 2007 |
+
"byteOffset": 26321920
|
| 2008 |
+
}
|
| 2009 |
+
],
|
| 2010 |
+
"md5sum": "aca564b8e952b26db4b32d881c11d348"
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"dataPath": "params_shard_53.bin",
|
| 2014 |
+
"format": "raw-shard",
|
| 2015 |
+
"nbytes": 39321600,
|
| 2016 |
+
"records": [
|
| 2017 |
+
{
|
| 2018 |
+
"name": "transformer.h.4.mixer.Wqkv.weight",
|
| 2019 |
+
"shape": [
|
| 2020 |
+
7680,
|
| 2021 |
+
2560
|
| 2022 |
+
],
|
| 2023 |
+
"dtype": "float16",
|
| 2024 |
+
"format": "f32-to-bf16",
|
| 2025 |
+
"nbytes": 39321600,
|
| 2026 |
+
"byteOffset": 0
|
| 2027 |
+
}
|
| 2028 |
+
],
|
| 2029 |
+
"md5sum": "a9530456770c3619145219284cdb6a82"
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"dataPath": "params_shard_54.bin",
|
| 2033 |
+
"format": "raw-shard",
|
| 2034 |
+
"nbytes": 52428800,
|
| 2035 |
+
"records": [
|
| 2036 |
+
{
|
| 2037 |
+
"name": "transformer.h.5.mlp.fc1.weight",
|
| 2038 |
+
"shape": [
|
| 2039 |
+
10240,
|
| 2040 |
+
2560
|
| 2041 |
+
],
|
| 2042 |
+
"dtype": "float16",
|
| 2043 |
+
"format": "f32-to-bf16",
|
| 2044 |
+
"nbytes": 52428800,
|
| 2045 |
+
"byteOffset": 0
|
| 2046 |
+
}
|
| 2047 |
+
],
|
| 2048 |
+
"md5sum": "beb5db238e6ed35d95b08a85bd9e01e9"
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"dataPath": "params_shard_55.bin",
|
| 2052 |
+
"format": "raw-shard",
|
| 2053 |
+
"nbytes": 52428800,
|
| 2054 |
+
"records": [
|
| 2055 |
+
{
|
| 2056 |
+
"name": "transformer.h.5.mlp.fc2.weight",
|
| 2057 |
+
"shape": [
|
| 2058 |
+
2560,
|
| 2059 |
+
10240
|
| 2060 |
+
],
|
| 2061 |
+
"dtype": "float16",
|
| 2062 |
+
"format": "f32-to-bf16",
|
| 2063 |
+
"nbytes": 52428800,
|
| 2064 |
+
"byteOffset": 0
|
| 2065 |
+
}
|
| 2066 |
+
],
|
| 2067 |
+
"md5sum": "00a4fa5a70deb767650b614fb10c8036"
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"dataPath": "params_shard_56.bin",
|
| 2071 |
+
"format": "raw-shard",
|
| 2072 |
+
"nbytes": 39321600,
|
| 2073 |
+
"records": [
|
| 2074 |
+
{
|
| 2075 |
+
"name": "transformer.h.5.mixer.Wqkv.weight",
|
| 2076 |
+
"shape": [
|
| 2077 |
+
7680,
|
| 2078 |
+
2560
|
| 2079 |
+
],
|
| 2080 |
+
"dtype": "float16",
|
| 2081 |
+
"format": "f32-to-bf16",
|
| 2082 |
+
"nbytes": 39321600,
|
| 2083 |
+
"byteOffset": 0
|
| 2084 |
+
}
|
| 2085 |
+
],
|
| 2086 |
+
"md5sum": "2ad9d1721f84c5f31dff3d7d7a7a96c7"
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"dataPath": "params_shard_57.bin",
|
| 2090 |
+
"format": "raw-shard",
|
| 2091 |
+
"nbytes": 52428800,
|
| 2092 |
+
"records": [
|
| 2093 |
+
{
|
| 2094 |
+
"name": "transformer.h.6.mlp.fc1.weight",
|
| 2095 |
+
"shape": [
|
| 2096 |
+
10240,
|
| 2097 |
+
2560
|
| 2098 |
+
],
|
| 2099 |
+
"dtype": "float16",
|
| 2100 |
+
"format": "f32-to-bf16",
|
| 2101 |
+
"nbytes": 52428800,
|
| 2102 |
+
"byteOffset": 0
|
| 2103 |
+
}
|
| 2104 |
+
],
|
| 2105 |
+
"md5sum": "09e347d5895f73bc819e435b579362b4"
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"dataPath": "params_shard_58.bin",
|
| 2109 |
+
"format": "raw-shard",
|
| 2110 |
+
"nbytes": 52428800,
|
| 2111 |
+
"records": [
|
| 2112 |
+
{
|
| 2113 |
+
"name": "transformer.h.6.mlp.fc2.weight",
|
| 2114 |
+
"shape": [
|
| 2115 |
+
2560,
|
| 2116 |
+
10240
|
| 2117 |
+
],
|
| 2118 |
+
"dtype": "float16",
|
| 2119 |
+
"format": "f32-to-bf16",
|
| 2120 |
+
"nbytes": 52428800,
|
| 2121 |
+
"byteOffset": 0
|
| 2122 |
+
}
|
| 2123 |
+
],
|
| 2124 |
+
"md5sum": "b5ab7ebe94255ed18aa03fcae28f918d"
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"dataPath": "params_shard_59.bin",
|
| 2128 |
+
"format": "raw-shard",
|
| 2129 |
+
"nbytes": 26327040,
|
| 2130 |
+
"records": [
|
| 2131 |
+
{
|
| 2132 |
+
"name": "transformer.h.4.mixer.out_proj.weight",
|
| 2133 |
+
"shape": [
|
| 2134 |
+
2560,
|
| 2135 |
+
2560
|
| 2136 |
+
],
|
| 2137 |
+
"dtype": "float16",
|
| 2138 |
+
"format": "f32-to-bf16",
|
| 2139 |
+
"nbytes": 13107200,
|
| 2140 |
+
"byteOffset": 0
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"name": "transformer.h.4.mixer.Wqkv.bias",
|
| 2144 |
+
"shape": [
|
| 2145 |
+
7680
|
| 2146 |
+
],
|
| 2147 |
+
"dtype": "float16",
|
| 2148 |
+
"format": "f32-to-bf16",
|
| 2149 |
+
"nbytes": 15360,
|
| 2150 |
+
"byteOffset": 13107200
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"name": "transformer.h.5.ln.bias",
|
| 2154 |
+
"shape": [
|
| 2155 |
+
2560
|
| 2156 |
+
],
|
| 2157 |
+
"dtype": "float16",
|
| 2158 |
+
"format": "f32-to-bf16",
|
| 2159 |
+
"nbytes": 5120,
|
| 2160 |
+
"byteOffset": 13122560
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"name": "transformer.h.5.ln.weight",
|
| 2164 |
+
"shape": [
|
| 2165 |
+
2560
|
| 2166 |
+
],
|
| 2167 |
+
"dtype": "float16",
|
| 2168 |
+
"format": "f32-to-bf16",
|
| 2169 |
+
"nbytes": 5120,
|
| 2170 |
+
"byteOffset": 13127680
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"name": "transformer.h.5.mlp.fc1.bias",
|
| 2174 |
+
"shape": [
|
| 2175 |
+
10240
|
| 2176 |
+
],
|
| 2177 |
+
"dtype": "float16",
|
| 2178 |
+
"format": "f32-to-bf16",
|
| 2179 |
+
"nbytes": 20480,
|
| 2180 |
+
"byteOffset": 13132800
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"name": "transformer.h.5.mlp.fc2.bias",
|
| 2184 |
+
"shape": [
|
| 2185 |
+
2560
|
| 2186 |
+
],
|
| 2187 |
+
"dtype": "float16",
|
| 2188 |
+
"format": "f32-to-bf16",
|
| 2189 |
+
"nbytes": 5120,
|
| 2190 |
+
"byteOffset": 13153280
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"name": "transformer.h.5.mixer.out_proj.bias",
|
| 2194 |
+
"shape": [
|
| 2195 |
+
2560
|
| 2196 |
+
],
|
| 2197 |
+
"dtype": "float16",
|
| 2198 |
+
"format": "f32-to-bf16",
|
| 2199 |
+
"nbytes": 5120,
|
| 2200 |
+
"byteOffset": 13158400
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"name": "transformer.h.5.mixer.out_proj.weight",
|
| 2204 |
+
"shape": [
|
| 2205 |
+
2560,
|
| 2206 |
+
2560
|
| 2207 |
+
],
|
| 2208 |
+
"dtype": "float16",
|
| 2209 |
+
"format": "f32-to-bf16",
|
| 2210 |
+
"nbytes": 13107200,
|
| 2211 |
+
"byteOffset": 13163520
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"name": "transformer.h.5.mixer.Wqkv.bias",
|
| 2215 |
+
"shape": [
|
| 2216 |
+
7680
|
| 2217 |
+
],
|
| 2218 |
+
"dtype": "float16",
|
| 2219 |
+
"format": "f32-to-bf16",
|
| 2220 |
+
"nbytes": 15360,
|
| 2221 |
+
"byteOffset": 26270720
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"name": "transformer.h.6.ln.bias",
|
| 2225 |
+
"shape": [
|
| 2226 |
+
2560
|
| 2227 |
+
],
|
| 2228 |
+
"dtype": "float16",
|
| 2229 |
+
"format": "f32-to-bf16",
|
| 2230 |
+
"nbytes": 5120,
|
| 2231 |
+
"byteOffset": 26286080
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"name": "transformer.h.6.ln.weight",
|
| 2235 |
+
"shape": [
|
| 2236 |
+
2560
|
| 2237 |
+
],
|
| 2238 |
+
"dtype": "float16",
|
| 2239 |
+
"format": "f32-to-bf16",
|
| 2240 |
+
"nbytes": 5120,
|
| 2241 |
+
"byteOffset": 26291200
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"name": "transformer.h.6.mlp.fc1.bias",
|
| 2245 |
+
"shape": [
|
| 2246 |
+
10240
|
| 2247 |
+
],
|
| 2248 |
+
"dtype": "float16",
|
| 2249 |
+
"format": "f32-to-bf16",
|
| 2250 |
+
"nbytes": 20480,
|
| 2251 |
+
"byteOffset": 26296320
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"name": "transformer.h.6.mlp.fc2.bias",
|
| 2255 |
+
"shape": [
|
| 2256 |
+
2560
|
| 2257 |
+
],
|
| 2258 |
+
"dtype": "float16",
|
| 2259 |
+
"format": "f32-to-bf16",
|
| 2260 |
+
"nbytes": 5120,
|
| 2261 |
+
"byteOffset": 26316800
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"name": "transformer.h.6.mixer.out_proj.bias",
|
| 2265 |
+
"shape": [
|
| 2266 |
+
2560
|
| 2267 |
+
],
|
| 2268 |
+
"dtype": "float16",
|
| 2269 |
+
"format": "f32-to-bf16",
|
| 2270 |
+
"nbytes": 5120,
|
| 2271 |
+
"byteOffset": 26321920
|
| 2272 |
+
}
|
| 2273 |
+
],
|
| 2274 |
+
"md5sum": "4ff6ed9e8c6244542ed1e0412969f707"
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"dataPath": "params_shard_60.bin",
|
| 2278 |
+
"format": "raw-shard",
|
| 2279 |
+
"nbytes": 39321600,
|
| 2280 |
+
"records": [
|
| 2281 |
+
{
|
| 2282 |
+
"name": "transformer.h.6.mixer.Wqkv.weight",
|
| 2283 |
+
"shape": [
|
| 2284 |
+
7680,
|
| 2285 |
+
2560
|
| 2286 |
+
],
|
| 2287 |
+
"dtype": "float16",
|
| 2288 |
+
"format": "f32-to-bf16",
|
| 2289 |
+
"nbytes": 39321600,
|
| 2290 |
+
"byteOffset": 0
|
| 2291 |
+
}
|
| 2292 |
+
],
|
| 2293 |
+
"md5sum": "aeceb9bec9d4f99791bab976eda24623"
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"dataPath": "params_shard_61.bin",
|
| 2297 |
+
"format": "raw-shard",
|
| 2298 |
+
"nbytes": 52428800,
|
| 2299 |
+
"records": [
|
| 2300 |
+
{
|
| 2301 |
+
"name": "transformer.h.7.mlp.fc1.weight",
|
| 2302 |
+
"shape": [
|
| 2303 |
+
10240,
|
| 2304 |
+
2560
|
| 2305 |
+
],
|
| 2306 |
+
"dtype": "float16",
|
| 2307 |
+
"format": "f32-to-bf16",
|
| 2308 |
+
"nbytes": 52428800,
|
| 2309 |
+
"byteOffset": 0
|
| 2310 |
+
}
|
| 2311 |
+
],
|
| 2312 |
+
"md5sum": "e28a069a898f94610d4f52f03a70a132"
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"dataPath": "params_shard_62.bin",
|
| 2316 |
+
"format": "raw-shard",
|
| 2317 |
+
"nbytes": 52428800,
|
| 2318 |
+
"records": [
|
| 2319 |
+
{
|
| 2320 |
+
"name": "transformer.h.7.mlp.fc2.weight",
|
| 2321 |
+
"shape": [
|
| 2322 |
+
2560,
|
| 2323 |
+
10240
|
| 2324 |
+
],
|
| 2325 |
+
"dtype": "float16",
|
| 2326 |
+
"format": "f32-to-bf16",
|
| 2327 |
+
"nbytes": 52428800,
|
| 2328 |
+
"byteOffset": 0
|
| 2329 |
+
}
|
| 2330 |
+
],
|
| 2331 |
+
"md5sum": "eaeef94a51cf1d83f8d5132defd7af77"
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"dataPath": "params_shard_63.bin",
|
| 2335 |
+
"format": "raw-shard",
|
| 2336 |
+
"nbytes": 39321600,
|
| 2337 |
+
"records": [
|
| 2338 |
+
{
|
| 2339 |
+
"name": "transformer.h.7.mixer.Wqkv.weight",
|
| 2340 |
+
"shape": [
|
| 2341 |
+
7680,
|
| 2342 |
+
2560
|
| 2343 |
+
],
|
| 2344 |
+
"dtype": "float16",
|
| 2345 |
+
"format": "f32-to-bf16",
|
| 2346 |
+
"nbytes": 39321600,
|
| 2347 |
+
"byteOffset": 0
|
| 2348 |
+
}
|
| 2349 |
+
],
|
| 2350 |
+
"md5sum": "b11cc2d4cb9dfdf49fc21a6d5ebfeaef"
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"dataPath": "params_shard_64.bin",
|
| 2354 |
+
"format": "raw-shard",
|
| 2355 |
+
"nbytes": 52428800,
|
| 2356 |
+
"records": [
|
| 2357 |
+
{
|
| 2358 |
+
"name": "transformer.h.8.mlp.fc1.weight",
|
| 2359 |
+
"shape": [
|
| 2360 |
+
10240,
|
| 2361 |
+
2560
|
| 2362 |
+
],
|
| 2363 |
+
"dtype": "float16",
|
| 2364 |
+
"format": "f32-to-bf16",
|
| 2365 |
+
"nbytes": 52428800,
|
| 2366 |
+
"byteOffset": 0
|
| 2367 |
+
}
|
| 2368 |
+
],
|
| 2369 |
+
"md5sum": "a511be3be0bf4534f77641d65119eafa"
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"dataPath": "params_shard_65.bin",
|
| 2373 |
+
"format": "raw-shard",
|
| 2374 |
+
"nbytes": 52428800,
|
| 2375 |
+
"records": [
|
| 2376 |
+
{
|
| 2377 |
+
"name": "transformer.h.8.mlp.fc2.weight",
|
| 2378 |
+
"shape": [
|
| 2379 |
+
2560,
|
| 2380 |
+
10240
|
| 2381 |
+
],
|
| 2382 |
+
"dtype": "float16",
|
| 2383 |
+
"format": "f32-to-bf16",
|
| 2384 |
+
"nbytes": 52428800,
|
| 2385 |
+
"byteOffset": 0
|
| 2386 |
+
}
|
| 2387 |
+
],
|
| 2388 |
+
"md5sum": "44343e3e55fe12e42a0fe3ce85be4edd"
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"dataPath": "params_shard_66.bin",
|
| 2392 |
+
"format": "raw-shard",
|
| 2393 |
+
"nbytes": 26327040,
|
| 2394 |
+
"records": [
|
| 2395 |
+
{
|
| 2396 |
+
"name": "transformer.h.6.mixer.out_proj.weight",
|
| 2397 |
+
"shape": [
|
| 2398 |
+
2560,
|
| 2399 |
+
2560
|
| 2400 |
+
],
|
| 2401 |
+
"dtype": "float16",
|
| 2402 |
+
"format": "f32-to-bf16",
|
| 2403 |
+
"nbytes": 13107200,
|
| 2404 |
+
"byteOffset": 0
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"name": "transformer.h.6.mixer.Wqkv.bias",
|
| 2408 |
+
"shape": [
|
| 2409 |
+
7680
|
| 2410 |
+
],
|
| 2411 |
+
"dtype": "float16",
|
| 2412 |
+
"format": "f32-to-bf16",
|
| 2413 |
+
"nbytes": 15360,
|
| 2414 |
+
"byteOffset": 13107200
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"name": "transformer.h.7.ln.bias",
|
| 2418 |
+
"shape": [
|
| 2419 |
+
2560
|
| 2420 |
+
],
|
| 2421 |
+
"dtype": "float16",
|
| 2422 |
+
"format": "f32-to-bf16",
|
| 2423 |
+
"nbytes": 5120,
|
| 2424 |
+
"byteOffset": 13122560
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"name": "transformer.h.7.ln.weight",
|
| 2428 |
+
"shape": [
|
| 2429 |
+
2560
|
| 2430 |
+
],
|
| 2431 |
+
"dtype": "float16",
|
| 2432 |
+
"format": "f32-to-bf16",
|
| 2433 |
+
"nbytes": 5120,
|
| 2434 |
+
"byteOffset": 13127680
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"name": "transformer.h.7.mlp.fc1.bias",
|
| 2438 |
+
"shape": [
|
| 2439 |
+
10240
|
| 2440 |
+
],
|
| 2441 |
+
"dtype": "float16",
|
| 2442 |
+
"format": "f32-to-bf16",
|
| 2443 |
+
"nbytes": 20480,
|
| 2444 |
+
"byteOffset": 13132800
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"name": "transformer.h.7.mlp.fc2.bias",
|
| 2448 |
+
"shape": [
|
| 2449 |
+
2560
|
| 2450 |
+
],
|
| 2451 |
+
"dtype": "float16",
|
| 2452 |
+
"format": "f32-to-bf16",
|
| 2453 |
+
"nbytes": 5120,
|
| 2454 |
+
"byteOffset": 13153280
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"name": "transformer.h.7.mixer.out_proj.bias",
|
| 2458 |
+
"shape": [
|
| 2459 |
+
2560
|
| 2460 |
+
],
|
| 2461 |
+
"dtype": "float16",
|
| 2462 |
+
"format": "f32-to-bf16",
|
| 2463 |
+
"nbytes": 5120,
|
| 2464 |
+
"byteOffset": 13158400
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"name": "transformer.h.7.mixer.out_proj.weight",
|
| 2468 |
+
"shape": [
|
| 2469 |
+
2560,
|
| 2470 |
+
2560
|
| 2471 |
+
],
|
| 2472 |
+
"dtype": "float16",
|
| 2473 |
+
"format": "f32-to-bf16",
|
| 2474 |
+
"nbytes": 13107200,
|
| 2475 |
+
"byteOffset": 13163520
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"name": "transformer.h.7.mixer.Wqkv.bias",
|
| 2479 |
+
"shape": [
|
| 2480 |
+
7680
|
| 2481 |
+
],
|
| 2482 |
+
"dtype": "float16",
|
| 2483 |
+
"format": "f32-to-bf16",
|
| 2484 |
+
"nbytes": 15360,
|
| 2485 |
+
"byteOffset": 26270720
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"name": "transformer.h.8.ln.bias",
|
| 2489 |
+
"shape": [
|
| 2490 |
+
2560
|
| 2491 |
+
],
|
| 2492 |
+
"dtype": "float16",
|
| 2493 |
+
"format": "f32-to-bf16",
|
| 2494 |
+
"nbytes": 5120,
|
| 2495 |
+
"byteOffset": 26286080
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"name": "transformer.h.8.ln.weight",
|
| 2499 |
+
"shape": [
|
| 2500 |
+
2560
|
| 2501 |
+
],
|
| 2502 |
+
"dtype": "float16",
|
| 2503 |
+
"format": "f32-to-bf16",
|
| 2504 |
+
"nbytes": 5120,
|
| 2505 |
+
"byteOffset": 26291200
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"name": "transformer.h.8.mlp.fc1.bias",
|
| 2509 |
+
"shape": [
|
| 2510 |
+
10240
|
| 2511 |
+
],
|
| 2512 |
+
"dtype": "float16",
|
| 2513 |
+
"format": "f32-to-bf16",
|
| 2514 |
+
"nbytes": 20480,
|
| 2515 |
+
"byteOffset": 26296320
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"name": "transformer.h.8.mlp.fc2.bias",
|
| 2519 |
+
"shape": [
|
| 2520 |
+
2560
|
| 2521 |
+
],
|
| 2522 |
+
"dtype": "float16",
|
| 2523 |
+
"format": "f32-to-bf16",
|
| 2524 |
+
"nbytes": 5120,
|
| 2525 |
+
"byteOffset": 26316800
|
| 2526 |
+
},
|
| 2527 |
+
{
|
| 2528 |
+
"name": "transformer.h.8.mixer.out_proj.bias",
|
| 2529 |
+
"shape": [
|
| 2530 |
+
2560
|
| 2531 |
+
],
|
| 2532 |
+
"dtype": "float16",
|
| 2533 |
+
"format": "f32-to-bf16",
|
| 2534 |
+
"nbytes": 5120,
|
| 2535 |
+
"byteOffset": 26321920
|
| 2536 |
+
}
|
| 2537 |
+
],
|
| 2538 |
+
"md5sum": "00162d75939eb0330d894bb26f8c5685"
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"dataPath": "params_shard_67.bin",
|
| 2542 |
+
"format": "raw-shard",
|
| 2543 |
+
"nbytes": 39321600,
|
| 2544 |
+
"records": [
|
| 2545 |
+
{
|
| 2546 |
+
"name": "transformer.h.8.mixer.Wqkv.weight",
|
| 2547 |
+
"shape": [
|
| 2548 |
+
7680,
|
| 2549 |
+
2560
|
| 2550 |
+
],
|
| 2551 |
+
"dtype": "float16",
|
| 2552 |
+
"format": "f32-to-bf16",
|
| 2553 |
+
"nbytes": 39321600,
|
| 2554 |
+
"byteOffset": 0
|
| 2555 |
+
}
|
| 2556 |
+
],
|
| 2557 |
+
"md5sum": "a8da9fa04ff9fbb632e404e55eb99acc"
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"dataPath": "params_shard_68.bin",
|
| 2561 |
+
"format": "raw-shard",
|
| 2562 |
+
"nbytes": 52428800,
|
| 2563 |
+
"records": [
|
| 2564 |
+
{
|
| 2565 |
+
"name": "transformer.h.9.mlp.fc1.weight",
|
| 2566 |
+
"shape": [
|
| 2567 |
+
10240,
|
| 2568 |
+
2560
|
| 2569 |
+
],
|
| 2570 |
+
"dtype": "float16",
|
| 2571 |
+
"format": "f32-to-bf16",
|
| 2572 |
+
"nbytes": 52428800,
|
| 2573 |
+
"byteOffset": 0
|
| 2574 |
+
}
|
| 2575 |
+
],
|
| 2576 |
+
"md5sum": "12e1356b7f7960e0b2005397eff796cd"
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"dataPath": "params_shard_69.bin",
|
| 2580 |
+
"format": "raw-shard",
|
| 2581 |
+
"nbytes": 52428800,
|
| 2582 |
+
"records": [
|
| 2583 |
+
{
|
| 2584 |
+
"name": "transformer.h.9.mlp.fc2.weight",
|
| 2585 |
+
"shape": [
|
| 2586 |
+
2560,
|
| 2587 |
+
10240
|
| 2588 |
+
],
|
| 2589 |
+
"dtype": "float16",
|
| 2590 |
+
"format": "f32-to-bf16",
|
| 2591 |
+
"nbytes": 52428800,
|
| 2592 |
+
"byteOffset": 0
|
| 2593 |
+
}
|
| 2594 |
+
],
|
| 2595 |
+
"md5sum": "dd5efaa435d1a33f296c59529b249f7c"
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"dataPath": "params_shard_70.bin",
|
| 2599 |
+
"format": "raw-shard",
|
| 2600 |
+
"nbytes": 39321600,
|
| 2601 |
+
"records": [
|
| 2602 |
+
{
|
| 2603 |
+
"name": "transformer.h.9.mixer.Wqkv.weight",
|
| 2604 |
+
"shape": [
|
| 2605 |
+
7680,
|
| 2606 |
+
2560
|
| 2607 |
+
],
|
| 2608 |
+
"dtype": "float16",
|
| 2609 |
+
"format": "f32-to-bf16",
|
| 2610 |
+
"nbytes": 39321600,
|
| 2611 |
+
"byteOffset": 0
|
| 2612 |
+
}
|
| 2613 |
+
],
|
| 2614 |
+
"md5sum": "4eecc2ff6bbef80cc85ff61963f44e9d"
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"dataPath": "params_shard_71.bin",
|
| 2618 |
+
"format": "raw-shard",
|
| 2619 |
+
"nbytes": 26286080,
|
| 2620 |
+
"records": [
|
| 2621 |
+
{
|
| 2622 |
+
"name": "transformer.h.8.mixer.out_proj.weight",
|
| 2623 |
+
"shape": [
|
| 2624 |
+
2560,
|
| 2625 |
+
2560
|
| 2626 |
+
],
|
| 2627 |
+
"dtype": "float16",
|
| 2628 |
+
"format": "f32-to-bf16",
|
| 2629 |
+
"nbytes": 13107200,
|
| 2630 |
+
"byteOffset": 0
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"name": "transformer.h.8.mixer.Wqkv.bias",
|
| 2634 |
+
"shape": [
|
| 2635 |
+
7680
|
| 2636 |
+
],
|
| 2637 |
+
"dtype": "float16",
|
| 2638 |
+
"format": "f32-to-bf16",
|
| 2639 |
+
"nbytes": 15360,
|
| 2640 |
+
"byteOffset": 13107200
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"name": "transformer.h.9.ln.bias",
|
| 2644 |
+
"shape": [
|
| 2645 |
+
2560
|
| 2646 |
+
],
|
| 2647 |
+
"dtype": "float16",
|
| 2648 |
+
"format": "f32-to-bf16",
|
| 2649 |
+
"nbytes": 5120,
|
| 2650 |
+
"byteOffset": 13122560
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"name": "transformer.h.9.ln.weight",
|
| 2654 |
+
"shape": [
|
| 2655 |
+
2560
|
| 2656 |
+
],
|
| 2657 |
+
"dtype": "float16",
|
| 2658 |
+
"format": "f32-to-bf16",
|
| 2659 |
+
"nbytes": 5120,
|
| 2660 |
+
"byteOffset": 13127680
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"name": "transformer.h.9.mlp.fc1.bias",
|
| 2664 |
+
"shape": [
|
| 2665 |
+
10240
|
| 2666 |
+
],
|
| 2667 |
+
"dtype": "float16",
|
| 2668 |
+
"format": "f32-to-bf16",
|
| 2669 |
+
"nbytes": 20480,
|
| 2670 |
+
"byteOffset": 13132800
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"name": "transformer.h.9.mlp.fc2.bias",
|
| 2674 |
+
"shape": [
|
| 2675 |
+
2560
|
| 2676 |
+
],
|
| 2677 |
+
"dtype": "float16",
|
| 2678 |
+
"format": "f32-to-bf16",
|
| 2679 |
+
"nbytes": 5120,
|
| 2680 |
+
"byteOffset": 13153280
|
| 2681 |
+
},
|
| 2682 |
+
{
|
| 2683 |
+
"name": "transformer.h.9.mixer.out_proj.bias",
|
| 2684 |
+
"shape": [
|
| 2685 |
+
2560
|
| 2686 |
+
],
|
| 2687 |
+
"dtype": "float16",
|
| 2688 |
+
"format": "f32-to-bf16",
|
| 2689 |
+
"nbytes": 5120,
|
| 2690 |
+
"byteOffset": 13158400
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"name": "transformer.h.9.mixer.out_proj.weight",
|
| 2694 |
+
"shape": [
|
| 2695 |
+
2560,
|
| 2696 |
+
2560
|
| 2697 |
+
],
|
| 2698 |
+
"dtype": "float16",
|
| 2699 |
+
"format": "f32-to-bf16",
|
| 2700 |
+
"nbytes": 13107200,
|
| 2701 |
+
"byteOffset": 13163520
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"name": "transformer.h.9.mixer.Wqkv.bias",
|
| 2705 |
+
"shape": [
|
| 2706 |
+
7680
|
| 2707 |
+
],
|
| 2708 |
+
"dtype": "float16",
|
| 2709 |
+
"format": "f32-to-bf16",
|
| 2710 |
+
"nbytes": 15360,
|
| 2711 |
+
"byteOffset": 26270720
|
| 2712 |
+
}
|
| 2713 |
+
],
|
| 2714 |
+
"md5sum": "7768f3a73f324517de18e1b8b7417da3"
|
| 2715 |
+
}
|
| 2716 |
+
]
|
| 2717 |
+
}
|
params_shard_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8830c58c1b6c6ba321cab6145763ec5770d3d7f7bff3f6cd1bfdc5b912c8c17
|
| 3 |
+
size 262144000
|
params_shard_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5797822d42c5eaa63f8f12cf564195a2564bd60d02e8baf8b58baa0f1152e059
|
| 3 |
+
size 52428800
|
params_shard_10.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1792964bf1b53d9fa62d425cc5780454a35b911d24da03e1521d7f2eb3bb581e
|
| 3 |
+
size 39321600
|
params_shard_11.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a6cf0768f6f99f97590ae516aad5b83bf0220ddd9235d598a8b12be4a8c9c60
|
| 3 |
+
size 52428800
|
params_shard_12.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30ce98981e19f20d288665f5a13b9344bf31964e903ea31b61b4a4cc3124d03a
|
| 3 |
+
size 52428800
|
params_shard_13.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8439ad1bfddf8c2584311a9ab51dad1b4df46d45de56efb7c00c722dc2f2e15
|
| 3 |
+
size 39321600
|
params_shard_14.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48a4c673f0698c4c890e51e8b42a56ff6a125c9ae78bae051f0e20d3a3aba41d
|
| 3 |
+
size 52428800
|
params_shard_15.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:577640665b2fb458e88fcfdfef2920641f4ac6a99f50a7bbc17d864e4fda26bc
|
| 3 |
+
size 52428800
|
params_shard_16.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f85d2be49f453f3f8ce98b42748266470bb1a4fb36017558e0fcbeddc5f9a603
|
| 3 |
+
size 26327040
|
params_shard_17.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e08106383d4ee773fd0624208a985aed52778c213d11d6f5b75bafd20a9b2220
|
| 3 |
+
size 39321600
|
params_shard_18.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:051d2ccf157dd13b97462776c67603739a434df017cf0fe2fdb251b0e9816107
|
| 3 |
+
size 52428800
|
params_shard_19.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ca84986a0af21e0bbab301c10d7e31b8b8a1ea7e560ac57e0ba78a072e71194
|
| 3 |
+
size 52428800
|
params_shard_2.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e83e9e878272f2041790a5baa7a925dd94609b2b2940901ae6dd2c7b33327740
|
| 3 |
+
size 52428800
|
params_shard_20.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44bf6e6e353bff7979471553050d6248466153f0cea4305fab5a73537e9281a5
|
| 3 |
+
size 39321600
|
params_shard_21.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfede3dfb22f419cba734087d4072cb1e63eedb97fd979d8eb051d3444979917
|
| 3 |
+
size 262144000
|
params_shard_22.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a378b6e1de0e85563eadd7e33812ac7a16f0432bc50ada982b35368fc9232d01
|
| 3 |
+
size 52428800
|
params_shard_23.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7dd5000049441cbf1b8c6540f1868313952070bad6507fcf671709efbe2af86
|
| 3 |
+
size 52428800
|
params_shard_24.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f793bf4193c5beec0dcfe558de27f97acc625214fcfd6e79464b1ba7b74c2e7
|
| 3 |
+
size 26327040
|
params_shard_25.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a295a4c0543dda8ec711f7d13ea374a09b28d27fa45bdaab4bbce875a6a91b5
|
| 3 |
+
size 39321600
|
params_shard_26.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:046611dea9ecd4b90f4d6b3683907f03aeed310465bda3b80b244ad9be078abf
|
| 3 |
+
size 52428800
|
params_shard_27.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a30c256412edf3ad41965d4e93ff4ae407c17fc9d600f3c0107a473dba3425
|
| 3 |
+
size 52428800
|
params_shard_28.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65a1064d4dec434b3bca15eaee5effba6299e0d1f4f3543c74941bb94004f1be
|
| 3 |
+
size 39321600
|
params_shard_29.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a4256e7b5fa9a66f3d5b2406602a75298fd9bca53c6ff0f3ec3a903f86babc
|
| 3 |
+
size 52428800
|
params_shard_3.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da08adb882824c1661fab21c9c91f306a0ce07ffdd0247e3674ad75bbf0caf5d
|
| 3 |
+
size 39321600
|
params_shard_30.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae5c9351d4e5fa0db74e54927d747cc20346f439bb8284980a4d225419d34688
|
| 3 |
+
size 52428800
|
params_shard_31.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e26cec49ddf81796d7e7cb83ed1bb4882a34e8f5212c62b1c30ff28b0c4f341
|
| 3 |
+
size 26327040
|
params_shard_32.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:844ba67732397a65e190b713a16b2f9baeb12f606109f761227ffe7d8d07c632
|
| 3 |
+
size 39321600
|
params_shard_33.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:906c45fc771287012b81ba51c32050dbb21d55c1df8fd175ab095898e4127309
|
| 3 |
+
size 52428800
|
params_shard_34.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af7c704ba13d9d49f85137aeb5c0bdf075cd1da97b61c22f6bc052d8010b6e9e
|
| 3 |
+
size 52428800
|
params_shard_35.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6869e27a0862120c1aadc089e118c2e31a3b33486a6063939823ac05120d707
|
| 3 |
+
size 39321600
|
params_shard_36.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd5445d28f8c06d3a8ccbf1213572bd5bf087b206df7bd8f0d22296badf7948f
|
| 3 |
+
size 52428800
|
params_shard_37.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e039a0b5e150963f131df8ee41bd0f1674ff69551b2860fd35584755d54f086
|
| 3 |
+
size 52428800
|
params_shard_38.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a1339bafea307a72848cd097550e1fb07ccb49e960baa73a32cf607ffc7eb7a
|
| 3 |
+
size 26327040
|
params_shard_39.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ffc3cace534009a19c55c00d1b884d24526ae4d778af281b9bfa640b80401ab
|
| 3 |
+
size 39321600
|
params_shard_4.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0f219e4b2a00824063ff1d5a9048b4918c9a95683a22933f79ad1347e90f08e
|
| 3 |
+
size 52428800
|
params_shard_40.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac54ce6612e225802bd185cc2118228fc643f068ab0652a21f231f031a4eddfa
|
| 3 |
+
size 52428800
|
params_shard_41.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f7443a70241dd0d3d1975358538d05f1c9dd58dee49c6759822e634c830cb17
|
| 3 |
+
size 52428800
|
params_shard_42.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b47add6bbfe056d593d24912bc45988b6af2a0e3ef90816cfde3e35619455a6
|
| 3 |
+
size 39321600
|
params_shard_43.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c40b565044bf48898f672aba36cd2ac5b30fb13d8c7ecdeebee6f80ac1ae86b6
|
| 3 |
+
size 52428800
|
params_shard_44.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:624681d060d7d8e6cf0ca7f502c69585dc393d6a381f5f6e3ad6bf6353b977b5
|
| 3 |
+
size 52428800
|
params_shard_45.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ad127c5ac7651e0405a8b2e0e4c9927d592fc898784920f54a088ea4649a3b9
|
| 3 |
+
size 26327040
|
params_shard_46.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e92ac55ad4a438e18e089f405a43015f1a2660adefa13d39d581a193a3bb7c9b
|
| 3 |
+
size 39321600
|
params_shard_47.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6afa7a343de99d1cee27c5568dd8651fc35a509edb3037754a4f33035f63a70b
|
| 3 |
+
size 52428800
|
params_shard_48.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a70860c4a9c1b670c2d351aee6f60a2e3158a27d68cd13f35de7a9cea3c23f3
|
| 3 |
+
size 52428800
|
params_shard_49.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe70de35f014b5d3602cfdd3c8b3495e9048c3c56b51e3fa55b7562bee0835a9
|
| 3 |
+
size 39321600
|
params_shard_5.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dda8d1b3d12b44a84ae0a23b61c7a5a4a54f6443184ee4487878f50b37f9ac6
|
| 3 |
+
size 52428800
|